Measure generation system, measure generation method, and measure generation program

Abstract

The present invention provides a measure generation system, a measure generation method and a measure generation program capable of creating a measure in response to a problem. This measure generation system includes: a business information reception means for receiving business information expressing a target business situation; an objective reception means for receiving, as character information, an objective for the target business which is set by a user; a measure information generation means for searching for relevant information in a prescribed network on the basis of a comparison between the business information and the objective, and generating measure information according to the search results; and an output means for outputting the measure information to a user.

Description

Measure generation system, measure generation method, and measure generation program

[0001] The present disclosure relates to a policy generation system, a policy generation method, and a policy generation program.

[0002] In recent years, technologies have been developed that analyze customer consumption behavior data and utilize it for marketing. For example, Patent Literature 1 discloses a technology that detects discrepancies between actual and predicted values ​​of events that cause sales changes (number of store visitors and environmental data (precipitation, temperature, etc.)), and appropriately corrects product sales forecasts.

[0003] International Publication No. 2018 / 061136

[0004] As disclosed in the above-mentioned Patent Document 1 and the like, various tools have been proposed for analyzing business data and extracting issues. However, it has not been easy to create suitable countermeasures, i.e., measures, for the issues using existing tools.

[0005] In view of the above-mentioned problems, an object of the present disclosure is to provide a policy generation system, a policy generation method, and a policy generation program that can create policies that contribute to achieving goals.

[0006] The policy generation system disclosed herein comprises a business information receiving means for receiving business information indicating the status of a target business; a goal receiving means for receiving text information of the goals of the target business set by a user; a policy information generation means for searching for related information in a specified network based on a comparison between the business information and the goals, and generating policy information according to the results of the search; and an output means for outputting the policy information to a user.

[0007] The policy generation method disclosed herein involves a computer receiving business information indicating the status of a target business, receiving goals for the target business set by a user as text information, searching for related information in a specified network based on a comparison between the business information and the goals, generating policy information based on the results of the search, and outputting the policy information to the user.

[0008] The policy generation program disclosed herein causes a computer to perform the following processes: accepting business information indicating the status of a target business; accepting goals for the target business set by a user as text information; searching for related information in a specified network based on a comparison between the business information and the goals, and generating policy information based on the results of the search; and outputting the policy information to a user.

[0009] The present disclosure makes it possible to provide a policy generation system, a policy generation method, and a policy generation program that can create policies for issues.

[0010] FIG. 1 is a block diagram showing a configuration of a measure generation device according to the present disclosure. FIG. 2 is a flowchart showing an example of the flow of a measure generation method according to the present disclosure. FIG. 3 is a block diagram showing a configuration of a measure generation system according to the present disclosure. FIG. 4 is a block diagram showing a configuration of a service request device capable of communicating with the measure generation system according to the present disclosure. FIG. 5 is a block diagram showing a configuration of a measure generation device according to the present disclosure. FIG. 6 is a flowchart showing an example of operation of the measure generation device. FIG. 7 is a diagram showing an example of an input screen. FIG. 8 is a diagram showing an example of business information. FIG. 9 is a diagram showing an example of related information. FIG. 10 is a flowchart showing an example of measure information generation processing. FIG. 11 is an example of output measure information. FIG. 12 is another example of output measure information. FIG. 13 is a sequence diagram showing an example of operation of the measure generation system when correcting a measure. FIG. 14 is

[0011] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are designated by the same reference numerals, and for clarity of explanation, duplicate explanations will be omitted as necessary.

[0012] First Embodiment An example of the configuration of a policy generation device 100 will be described below with reference to Fig. 1. The policy generation device 100 includes a project information receiving unit 110, a goal receiving unit 120, a policy information generation unit 130, and an output unit 140.

[0013] The business information receiving unit 110 receives business information. The business information is information indicating the status of a target business for which a user wants to generate a policy. Here, the user is a user of the policy generation device 100. However, the user and the operator using the policy generation device 100 do not necessarily have to be the same person. For example, the policy generation device 100 may be operated by an operator who has heard the user's goals, etc. The business information may be, for example, information regarding sales of a retail store run by the user and information regarding the retail store's customers. An example of such business information is business information including words related to customer attributes of the target business. Here, customer attributes are information about customers, and are at least one word that is associated with the customer's image. The business information is text information. The business information may be diagram information such as graphs and photographs converted into text information.

[0014] The goal receiving unit 120 receives the goal of the target business as text information. The goal of the target business is set by the user and may be, for example, a sentence such as "Improve sales at store X." Alternatively, the goal of the target business may be one or more words such as "Improve sales at store X."

[0015] The policy information generation unit 130 compares the business information received by the business information receiving unit 110 with the goal received by the goal receiving unit 120 to search for related information in a predetermined network. Then, the policy information generation unit 130 generates policy information according to the search results. Here, the predetermined network is a network for searching for related information related to the input words. The policy information generation unit 130 searches for related information based on the comparison between the business information and the goal. At this time, the policy information generation unit 130 may perform natural language processing on at least one of the business information and the goal.

[0016] The policy information generation unit 130, for example, searches for related information related to both the business information and the goal, and generates policy information based on at least one piece of related information. Specifically, for example, if the business information is "Existing customers of store X are women in their 20s" and the goal is "Increase the average customer spending of existing customers at store X by 100 yen," the policy information generation unit 130 searches a predetermined network for "a list of products frequently purchased by women in their 20s at stores of the same type as store X." Then, based on the search results, the policy information generation unit 130 generates a policy such as "Place snacks purchasable for approximately 120 yen near the lunch box section." In this way, the policy generation device 100 can generate information about policies to achieve the goals set by the user, i.e., policies for addressing challenges. The policy information is information about the policy, and may include, for example, the name of the policy and multiple related words that constitute the policy.

[0017] The output unit 140 outputs the policy information generated by the policy information generation unit 130. The method for outputting the policy information is not particularly limited, and the policy information may be output as text data or a network diagram, for example.

[0018] Next, an example of a policy generation method according to the present disclosure will be described with reference to FIG. 2 . First, the business information receiving unit 110 receives business information for a target business (step S101). Next, the goal receiving unit 120 receives the goal of the target business as text information (step S102). Next, the policy information generating unit 130 searches for related information in a predetermined network based on a comparison between the business information received in step S101 and the goal received in step S102, and generates policy information based on the search results (step S103). Next, the output unit 140 outputs the policy information generated in step S103 to the user (step S104).

[0019] In this way, the policy generation method using the policy generation device 100 receives business information and goals, and generates policy information by searching for related information. Therefore, it is possible to create measures for the received goals, i.e., issues.

[0020] The policy generation device 100 includes a processor, memory, and storage device (not shown). The storage device stores a computer program that implements the processing of the policy generation method according to this embodiment. The processor then loads the computer program from the storage device into the memory and executes the computer program. This allows the processor to realize the functions of the business information receiving unit 110, the goal receiving unit 120, the policy information generating unit 130, and the output unit 140.

[0021] Alternatively, each component of the policy generation device 100 may be realized by dedicated hardware. Furthermore, some or all of the components of each device may be realized by general-purpose or dedicated circuits, processors, etc., or a combination of these. These may be configured by a single chip, or by multiple chips connected via a bus. Some or all of the components of each device may be realized by a combination of the above-mentioned circuits, etc., and a program. Furthermore, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field-Programmable Gate Array), a quantum processor (quantum computer control chip), etc., may be used as the processor.

[0022] Furthermore, when some or all of the components of the policy generation device 100 are realized by multiple information processing devices, circuits, etc., the multiple information processing devices, circuits, etc. may be centrally or decentralized. For example, the information processing devices, circuits, etc. may be realized as a client-server system, a cloud computing system, or the like, in which each is connected via a communication network. Furthermore, the functions of the policy generation device 100 may be provided in a SaaS (Software as a Service) format.

[0023] Second Embodiment Next, an example configuration of a policy generation system 200 will be described with reference to Fig. 3. The policy generation system 200 is an information system that receives business information and goals from a service request device 600 and generates policy information for achieving the goals. The policy generation system 200 includes a related information network 300, a large-scale language model 310, and a policy generation device 400. The related information network 300, the large-scale language model 310, and the policy generation device 400 are communicatively connected via a network 500. Here, the network 500 is a network in which information and communication devices are connected via wired or wireless communication lines, and may be a network that is accessible only to some information devices, or may be a network that can be used by an unspecified number of people, such as the Internet.

[0024] The related information network 300 is a network through which the policy generation device 400 can search for related information. The policy generation device 400 uses the related information network 300 to search for and acquire related information related to a predetermined word. Here, the predetermined word is, for example, a word related to business information, goals, etc., and specifically, may be a word obtained by natural language processing of the business information, goals, etc., which are text information.

[0025] The large-scale language model 310 is a so-called LLM (Large Language Model), and performs natural language processing of business information, goals, etc. received by the policy generation device 400. The large-scale language model 310 summarizes text data such as business information and goals, for example.

[0026] The large-scale language model and / or LLM may be realized, for example, by a neural network. The neural network includes a plurality of artificial neurons, each having a synapse connecting the artificial neurons. Each synapse has a weight. When such a neural network receives an input, it performs a calculation using the weight associated with each synapse and produces an output according to the input.

[0027] A model representing the connection relationship between neurons and synapses is stored in memory, for example, in the form of software. Alternatively, the model may be realized as a dedicated circuit. Similarly, the weights of each synapse are stored in memory, for example, in the form of software. Alternatively, a circuit representing the weights may be implemented in a dedicated circuit. Note that when multiple models are used to configure a large-scale language model and / or LLM, all of the models do not necessarily need to be stored in the same memory.

[0028] There are a variety of models using such neural networks, and a wide variety of models, such as a Transformer, a Convolutional Neural Network (CNN), or a Recurrent Neural Network (RNN), may be adopted or substituted to realize a large-scale language model and / or an LLM.

[0029] Next, an example configuration of a service request device 600 capable of communicating with the policy generation system 200 will be described with reference to Fig. 4. As shown in Fig. 4, the policy generation system 200 is connected to the service request device 600. The service request device 600 is an information processing device that requests the policy generation system 200 to generate a policy for a target business, and is owned, for example, by the user requesting policy generation, i.e., the business operator conducting the target business. As will be described in detail later, the service request device 600 transmits business information and goals of the target business for which a policy is to be generated to the policy generation system 200, and receives policy information related to at least one policy from the policy generation system 200.

[0030] The service request device 600 includes a business information database 610, a business information transmission unit 620, a goal transmission unit 630, a policy information reception unit 640, and a correction instruction transmission unit 650. The business information database 610 stores business information of the target business. The business information database 610 may store the business information as text data, i.e., character information, or may store the business information in other formats such as graphs or photographs. Specific examples of the business information stored in the business information database 610 include sales data, customer information, sales promotion event implementation records, customer survey results, etc., for the retail store run by the user.

[0031] The business information transmission unit 620 is a communication means that extracts business information specified by a user from the business information stored in the business information database 610 and transmits the extracted business information to the policy generation system 200. When the business information is stored in a format other than character information, the business information transmission unit 620 may convert the business information into character information using an external service and transmit the converted business information to the policy generation system 200. Here, the external service is a service that converts data such as graphs into character information, and may be provided as a cloud service, for example. Business information stored in a format other than character information typically has a larger data volume than business information stored as character information. Therefore, converting business information stored in a format other than character information into character information before transmitting it can reduce the amount of data transmitted. The process of converting business information stored in a format other than character information into character information may be performed on the policy generation system 200 side. In this case, the business information transmission unit 620 transmits business information stored in a format other than character information to the policy generation system 200 without converting it into character information.

[0032] The goal sending unit 630 is a communication means that sends the goals for the target business entered by the user to the policy generation system 200. The policy generation system 200 is configured to output policy information upon receiving business information. The policy information receiving unit 640 is a communication means that receives policy information from the policy generation system 200. The user reviews the received policy information and inputs instructions to correct the policy information as necessary. The correction instructions are text information that includes words for correcting the policy information. The correction instruction sending unit 650 is a communication means that sends the correction instructions entered by the user to the policy generation system 200.

[0033] Next, an example configuration of the policy generation device 400 will be described with reference to FIG. 5 . The policy generation device 400 is an example of the policy generation device 100 described above. The policy generation device 400 is an information processing device that performs policy generation processing, etc., and is, for example, a server device realized by a computer. The policy generation device 400 may be redundantly configured with multiple servers, and each functional block may be realized by multiple computers. The policy generation device 400 includes a memory 410, a communication unit 420, a storage unit 430, and a control unit 440.

[0034] The memory 410 is a storage area that temporarily stores the processing contents of the control unit 440, and is a volatile storage device such as a RAM (Random Access Memory). The communication unit 420 is an interface that communicates with the outside of the policy generation device 400. The storage unit 430 is a storage device that stores a program 431 and the like. The program 431 is a computer program that implements the policy generation processing according to the present disclosure.

[0035] The control unit 440 includes a business information receiving unit 441, a goal receiving unit 442, a policy information generating unit 443, an output unit 444, and a correction receiving unit 445. The control unit 440 is a control device that controls the operation of the policy generating device 400, and is, for example, a processor such as a CPU. The control unit 440 loads the program 431 from the storage unit 430 into the memory 410 and executes it. As a result, the control unit 440 realizes the functions of the business information receiving unit 441, the goal receiving unit 442, the policy information generating unit 443, the output unit 444, and the correction receiving unit 445.

[0036] When requesting the generation of a policy, the service request device 600 transmits business information and goals of the target business for which the policy has been generated to the policy generation device 400. Upon receiving the business information, the business information receiving unit 441 accepts input of the business information. If the received business information is information other than text information, the business information receiving unit 441 converts the received business information into text information using the external service described above before accepting the information. Upon receiving the goal, the goal receiving unit 442 accepts input of the goal.

[0037] The policy information generation unit 443 searches for related information in the related information network 300 based on a comparison of the business information and the goal, and generates policy information according to the search results. At this time, the policy information generation unit 443 may summarize text information for at least one of the business information and the goal using the large-scale language model 310. For example, when a sentence input by a user is received as the goal, the policy information generation unit 443 may use the large-scale language model 310 to acquire words, i.e., keywords, that succinctly indicate the content of the sentence.

[0038] The policy information generation unit 443 may also perform attribute extension for at least one of the business information and the goals. Attribute extension is a technique for extending attributes included in information. For example, the policy information generation unit 443 may extract attribute information included in the business information as first attribute information, extend the first attribute information, and link second attribute information to the business information. The first attribute information is information that may be related to the consumption behavior of existing customers, etc. Note that consumption behavior refers to, for example, purchasing products, services, etc. Furthermore, such behavior is not limited to behavior performed in a physical store, but may also include online shopping performed on the Internet. Specifically, the first attribute information is, for example, information that can be extracted from consumption behavior information of existing customers included in the business information. Specifically, the first attribute information may include, for example, information related to a product, such as the product name of a product purchased by a registered member at a retail store and product attribute information previously assigned to the product.

[0039] Consumption behavior information includes the consumption behavior history of existing customers, etc., and specifically, is information linking a specific person to the consumption behavior history of that person. The consumption behavior information may be information linking a specific person to the consumption behavior history of that person directly or indirectly. Examples of consumption behavior information include information linking a member who has registered with a retail store to the member's purchase history at the retail store. The purchase history included in the consumption behavior information includes, for example, the date and time of a product purchase, the purchase amount, and the name of the purchased product. The consumption behavior information may also include basic attribute information of the member. The basic attribute information is basic attribute information about the member, such as demographic attributes, geographic attributes, and behavioral attributes. Demographic attributes are demographic attributes, such as the member's age and gender. Geographic attributes are geographic attributes, such as the climate, culture, and economy specific to the region where the member resides. Behavioral attributes are behavioral attributes, such as the member's frequency of using products and services, their purpose, purchase history, and range of activities.

[0040] The second attribute information is character information obtained by expanding the first attribute information. The second attribute information is associated with the corresponding member. The second attribute information is identified, for example, by processing the first attribute information using one or a combination of expansion, conversion, and estimation. Specifically, the policy information generation unit 443 may identify character information having a similar concept or meaning to the first attribute information, which is character information, as the second attribute information. The policy information generation unit 443 may determine whether the character information identified as the second attribute information has a similar concept or meaning to the first attribute information by performing natural language processing. One aspect of such second attribute information is psychographic attributes expanded based on the first attribute information. If the first attribute information is the name of a product purchased by a member, the second attribute information may be, for example, a word or words that are expanded from the purchased product name and that represent the member's image. Specifically, if the first attribute information is "pet supplies," the second attribute information may be "animal lover," "family-friendly," "safety measures," etc.

[0041] The output unit 444 outputs the policy information generated by the policy information generation unit 443 and transmits it to the service request device 600. The user views the received policy information and, if necessary, inputs an instruction to correct the policy information to the service request device 600. The correction receiving unit 445 receives the correction instruction received from the service request device 600 as text information.

[0042] Next, an example of the operation of the policy generation device 400 will be described with reference to Fig. 6. When business information and a goal are received from the service request device 600, the business information receiving unit 441 receives the business information (step S201), and the goal receiving unit 442 receives the goal (step S202).

[0043] FIG. 7 shows an example of an input screen on which a user inputs goals and the like into the service request device 600. As shown in FIG. 7, the input screen has input fields for the user to input information necessary for generating policy information. The input screen is designed so that the user inputs information necessary for generating policy information, for example, by answering a plurality of questions. After inputting answers to the questions displayed on the input screen, the user presses a calculation start button displayed on the input screen. When the calculation start button is pressed, the service request device 600 transmits business information and goals to the policy generation device 400 based on the input answers. The business information transmitted to the policy generation device 400 is selected from business information stored in the business information database 610 in the service request device 600. The business information transmitted to the policy generation device 400 may be selected by the user as shown in FIG. 7, or may be selected by the service request device 600.

[0044] The service request device 600 may also transmit information on the external environment related to the target business along with the business information. Here, the information on the external environment refers to information other than the information stored in the business information database 610. For example, the information on the external environment is information acquired from outside the policy generation system 200, such as the consumer price index, exchange rate data, temperature data, external website data, and large-scale language model data, and is information that may be related to the target business. When the business information receiving unit 441 receives the information on the external environment in addition to the business information, it receives the received information on the external environment together with the business information.

[0045] FIG. 8 is an example of business information transmitted to the policy generation device 400. FIG. 8 shows a graph ranking the top-selling products at a specific retail store. When a graph such as that shown in FIG. 8 is received, the business information receiving unit 441 converts the graph into text information using an external service. The text information converted from the graph shown in FIG. 8 may include, for example, multiple words such as "XX store, February, sales ranking by medium category, 1st place: home repair materials, XX yen, 2nd place: light bulbs, XX store, ..."

[0046] Furthermore, the policy information generating unit 443 may summarize the text information of the received business information using the large-scale language model 310. For example, an example of the summarized text information obtained by converting the graph shown in Fig. 8 above is a sentence such as "At store X, DIY products such as home repair materials and repair tools are selling very well. Also, at store X, pet-related products seem to be selling well."

[0047] Returning to FIG. 6 , the explanation will be continued. Next, the policy information generation unit 443 generates policy information based on the business information received in step S201 and the goal received in step S202 (step S203). Note that, if the policy information generation unit 443 receives information on the external environment in step S201, it generates policy information taking the information on the external environment into account. Next, the output unit 444 outputs the policy information generated in step S203 (step S204). The user checks the output policy information and inputs correction instructions to the service request device 600 as necessary. The service request device 600 transmits the input correction instructions to the policy generation device 400.

[0048] When the correction receiving unit 445 receives a correction instruction, it accepts the correction instruction. If the correction receiving unit 445 accepts a correction instruction, i.e., if a correction instruction has been given (Yes in step S205), the policy information generation unit 443 corrects the policy information based on the correction instruction (step S206). The output unit 444 outputs the policy information corrected in step S206 (step S204). If the correction receiving unit 445 has not accepted a correction instruction, i.e., if there has been no correction instruction (No in step S205), the policy generation device 400 ends the series of operations.

[0049] Next, an example of step S203 shown in FIG. 6 , i.e., the policy information generation process, will be described with reference to FIG. 9 . In the example described below, it is assumed that a goal is input to increase sales by 5% at a home improvement store having a sales ranking as shown in FIG. 8 . In the example shown in FIG. 9 , the policy generation device 400 generates policy information by attribute-expanding the business information. First, the policy information generation unit 443 extracts first attribute information from the business information, which is text information (step S301). If the business information includes the age and gender of the home improvement store's existing customers, text information such as "50% of existing customers are men in their 40s, and 70% are men in their 30s to 50s" is extracted as the first attribute information.

[0050] Next, the policy information generation unit 443 expands the first attribute information extracted in step S301 to identify second attribute information (step S302). The second attribute information identified in step S302 is, for example, a plurality of words indicating the hobbies and preferences of the existing customer, which are expanded from the existing customer's basic attribute information and purchase history. Since there are usually multiple existing customers, the expanded second attribute information for each existing customer may be organized in a ranking format. FIG. 10 shows an example of second attribute information of existing customers organized in a ranking format. Note that for convenience of explanation, FIG. 10 shows the ranking in table format, but the policy information generation unit 443 processes the ranking as text information. The method for organizing the ranking format is not particularly limited. For example, among the second attribute information assigned to multiple existing customers, second attribute information assigned to a greater number of existing customers may be ranked higher.

[0051] The example shown in FIG. 10 illustrates a case in which the second attribute information is identified solely from the business information received from the service request device 600. However, the second attribute information may also be identified using information registered in an external database, etc., in addition to the business information received from the service request device 600. For example, the policy information generation unit 443 may use an external database containing pre-expanded attribute information on existing customers of other retail stores to estimate existing customers of the other retail stores whose second attribute information is similar to that of existing customers of the home improvement center. The policy information generation unit 443 may then further identify the second attribute information of the existing customers of the home improvement center based on the consumption behavior information of the existing customers of the other retail stores who are estimated to be similar. Alternatively, the policy information generation unit 443 may transmit the business information received from the service request device 600 to an external system that can use the external database and acquire the consumption behavior information of the existing customers of the other retail stores who are estimated to be similar in the external system. In this case, the policy information generation unit 443 may identify the second attribute information of the existing customers of the home improvement center based on the acquired consumption behavior information of the existing customers of the other retail stores.

[0052] Returning to FIG. 9 , the explanation continues. Next, the policy information generation unit 443 searches for related information related to the second attribute information identified in step S302. Specifically, the policy information generation unit 443 inputs the character information identified as the second attribute information to the related information network 300 and acquires the output as related information related to the second attribute information. When character information such as a word or a sentence is input, the related information network 300 outputs information related to the character information. Examples of information output by the related information network 300 include articles on websites and information summarizing the articles. For example, if the second attribute information of the business information is "middle-aged men interested in DIY," examples of related information for the business information include articles with the main theme that "videos about renovating homes by yourself have recently become popular among male viewers."

[0053] Next, the policy information generation unit 443 searches for related information related to the goal (step S304). Specifically, the policy information generation unit 443 inputs the goal, which is text information, to the related information network 300 and acquires the output as related information related to the goal. At this time, the policy information generation unit 443 may summarize the goal using the large-scale language model 310 and then input the summarized information to the related information network 300. For example, if the second attribute information of the goal is "a 5% increase in sales," an example of related information for the goal would be an article that states, "Encouraging impulse buying is effective in increasing sales by about 5%."

[0054] Next, the policy information generation unit 443 compares the search results from step S303 and step S304 and extracts mutually related search results (step S305). Here, "related search results" refers to similar words contained in the search results or words further extended from the search results. From the specific example of related information for business information described above, "Recently, videos of people renovating their homes themselves have become popular among male viewers," "Purchasing DIY supplies" is extended. Similarly, from the specific example of related information for goals, "Encouraging impulse purchases is effective in increasing sales by about 5%," "Purchasing products that suit the buyer's hobbies" is extended. Since "DIY supplies" are products that suit the hobbies of people who like DIY, they are considered a specific example of "products that suit the buyer's hobbies." Therefore, "Purchasing DIY supplies" and "Purchasing products that suit the buyer's hobbies" are considered to be similar words. Therefore, the above-mentioned related information is extracted in step S305 as being related to each other.

[0055] Next, the policy information generation unit 443 generates policy information based on at least a portion of the search results extracted in step S305 (step S306). Specifically, the policy information generation unit 443 generates policy information for achieving the goal using text information contained in the search results extracted in step S305. The generation of policy information based on the search results may be realized using the large-scale language model 310. The policy information is information in which related words are linked to the policy name. The policy name is a word that succinctly indicates the content of the policy. The related words are text information that constitutes the policy and indicate the content of the policy in detail. The policy information generation unit 443 may further generate policy information that includes information about references that serve as the basis for selecting the related words. The information about the references may be, for example, the URLs of websites that serve as the basis for selecting the related words. FIG. 11 shows an example of policy information output to the service request device 600. As shown in FIG. 11, the related words may include one or more sentences.

[0056] Although FIG. 11 shows a case where the policy information is displayed as text information, the method of displaying the policy information in the service request device 600 is not particularly limited. For example, the policy information may be displayed as a network diagram in which the policy names and related words are visually associated, as shown in FIG. 12. When the policy information is displayed as a network diagram as shown in FIG. 12, for example, a plurality of icons may be displayed, with related icons connected by lines. When the cursor is placed over each icon, the content of the icon may be displayed as text information. Icon 800 is an icon indicating a goal. Icons 810, 820, and 830 connected to icon 800 are icons indicating the policy names of each policy.

[0057] Among the icons indicating the names of the measures, those that indicate measures that the measure generation device 400 has determined to be particularly effective may be eye-catching icons. In the example shown in Fig. 12, icons 810, 820, and 830 are used in this order of decreasing size, with icon 810 being the eye-catching icon. Methods for making an icon eye-catching include using a flashy color or a different shape, in addition to increasing its size.

[0058] Icons 814 and 815 connected to icon 811 indicate related words linked to the policy name indicated by icon 811. When policy information includes information about a reference destination, the information about the reference destination may be indicated in an icon linked to the icon indicating the policy name, such as icons 814 and 815.

[0059] Next, referring to FIG. 13 , an example of the operation of the policy generation system 200 when correcting the policy information in step S206 shown in FIG. 6 will be described. The user checks the policy information transmitted to the service request device 600 and inputs a correction instruction to the service request device 600 as necessary. The correction instruction input by the user is not particularly limited and may be, for example, an instruction to make changes to the output policy information or an instruction to generate policy information other than the output policy information. For example, the policy information shown in FIG. 11 is a policy mainly aimed at increasing the purchase amount of existing customers. However, if the policy desired by the user is to attract new customers, the user may input a correction instruction such as, "Please generate a policy to increase sales by attracting new customers."

[0060] The service request device 600 transmits the input correction instruction to the policy generation system 200 (step S401). Upon receiving the correction instruction, the correction receiving unit 445 accepts the correction instruction. Next, the policy information generation unit 443 searches for related information regarding the business information and the goal, taking the accepted correction instruction into consideration (S402). For example, in the above example, the policy information generation unit 443 searches for the first related information, "Women, particularly women in their 20s to 40s, are likely to be potential new customers," from the first attribute information extracted from the business information, "Existing customers are 50% men in their 40s and 70% men in their 30s to 50s." Next, the policy information generation unit 443 searches for the second related information, "Information provided by SNS influencers has a significant impact on the consumption behavior of young women." Next, the policy information generation unit 443 searches for the third related information, "Mr. / Ms. X is an influencer who has recently become popular among women," from the second related information.

[0061] The policy information generation unit 443 generates new policy information that takes into account the correction instructions based on the related information searched in step S402 (step S403). Specifically, for example, the policy information generation unit 443 generates policy information with a policy name of "Request popular influencer XX to advertise the store" based on the first to third related information described above. The output unit 444 transmits the new policy information to the service request device 600 (step S404).

[0062] The user may not be able to input all of the intended content when inputting goals and the like as a preliminary step to step S201 shown in Fig. 6. Therefore, the policy generation device 400 can generate policy information that more accurately reflects the user's intentions by accepting a correction instruction and correcting the policy information according to the procedure shown in Fig. 13 or the like.

[0063] Other Embodiments In the above embodiment, the case where business information is received along with a goal has been described. However, the business information may be pre-stored in a database within the policy generation system 200 or an external database. Furthermore, the system may be equipped with a function for calculating the number of generated policies or a fee based on the number of generated policies. Alternatively, information indicating a plan may be received and policies may be generated within a range corresponding to the plan. Furthermore, the content of the generated policies may be changed depending on the fee or plan. For example, if a user is identified as having subscribed to a high-priced plan, the policy generation system 200 may present policies with more substantial content compared to users subscribed to a low-priced plan. "Substantial content" means, for example, that more information is referenced when generating the policies. Such information may be information obtained from the business information, information on extended attributes, or other information. Alternatively, the generated policies may simply have a larger character count.

[0064] When performing output in each embodiment, the display content may be changed based on information about the display to which the output is made. Examples of the display information include the size of the display and the ratio of the vertical length to the horizontal length of the display. Based on the display information, the display content may be changed, for example, so that the larger the display size, the larger the size of characters, graphs, and other figures. In this case, an upper limit may be set so that the display content is not displayed larger than a predetermined size on the display. Similarly, the smaller the display size, the smaller the size of characters, graphs, and other figures. Furthermore, a lower limit may be set so that the display content is not displayed smaller than a predetermined size on the display. In addition, the display position may be changed, or certain items may not be displayed on the same screen.

[0065] In another aspect, the display content may be changed depending on the processing power of the information processing device that performs the processing for displaying on the display. For example, when the processing power of the information processing device is low, the content to be displayed or the amount of information to be displayed may be reduced compared to when the processing power is high. Regarding the processing power, predetermined specifications such as the memory size of the information processing device may be referenced, or the operating status or task execution status of the processor of the information processing device may be referenced.

[0066] <Example of Hardware Configuration> Hereinafter, with reference to FIG. 14, a case where each functional configuration of the policy generation device according to the present disclosure is realized by a combination of hardware and software will be described.

[0067] The policy generation device according to the present disclosure can achieve the above-described functions using a computer 11 including the hardware configuration shown in the figure. The computer 11 may be a portable computer such as a smartphone or tablet terminal, or a stationary computer such as a PC. The computer 11 may be a dedicated computer designed to realize each device, or may be a general-purpose computer. The computer 11 can achieve the desired functions by installing a specific program.

[0068] The computer 11 has a bus 21, a processor 30, a memory 40, a storage device 50, an input / output interface 60 (an interface is also called an I / F (Interface)), and a network interface 70. The bus 21 is a data transmission path through which the processor 30, the memory 40, the storage device 50, the input / output interface 60, and the network interface 70 transmit and receive data to and from each other. However, the method of connecting the processor 30 and the like to each other is not limited to bus connection.

[0069] The processor 30 is a processor such as a CPU, a GPU, an FPGA, etc. The memory 40 is a main storage device realized using a RAM (Random Access Memory) or the like.

[0070] The storage device 50 is an auxiliary storage device realized using a hard disk, SSD, memory card, ROM (Read Only Memory), etc. The storage device 50 stores programs for realizing desired functions. The processor 30 reads these programs into the memory 40 and executes them to realize the various functional components of each device.

[0071] The input / output interface 60 is an interface for connecting the computer 11 with input / output devices. For example, the input / output interface 60 is connected to an input device such as a keyboard and an output device such as a display device.

[0072] The network interface 70 is an interface for connecting the computer 11 to a network.

[0073] Although an example of a hardware configuration for the present disclosure has been described above, the above-described embodiment is not limited to this. Any processing in the present disclosure can also be realized by causing a processor to execute a computer program.

[0074] In the above examples, the program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The program may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0075] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0076] Each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0077] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0078] (Appendix A1) A policy generation system comprising: a business information receiving means for receiving business information indicating the status of a target business; a goal receiving means for receiving text information of the target business set by a user; a policy information generating means for searching for related information in a specified network based on a comparison between the business information and the goal, and generating policy information according to the results of the search; and an output means for outputting the policy information to a user.

[0079] (Appendix A2) The policy generation system described in Appendix A1, wherein the policy information generation means accepts the business information as text information, extracts first attribute information from the business information, identifies second attribute information that expands the extracted first attribute information, searches for the identified second attribute information and the related information related to the goal, and generates the policy information for achieving the goal based on the related information.

[0080] (Appendix A3) The policy generation system according to appendix A1 or A2, wherein the project information receiving means also receives information on an external environment related to the target project.

[0081] (Appendix A4) The policy generation system according to any one of Appendices A1 to A3, wherein the business information receiving means receives the business information including words related to customer attributes of the target business.

[0082] (Appendix A5) The policy generation system according to any one of Appendices A1 to A4, wherein the business information receiving means receives, as the business information, character information summarized in a predetermined large-scale language model.

[0083] (Appendix A6) The policy generation system according to any one of Appendices A1 to A5, wherein the policy information generation means generates the policy information including a policy name indicating at least one policy and a plurality of related words that constitute the policy.

[0084] (Supplementary Note A7) The policy generation system according to Supplementary Note A6, wherein the policy information generation means generates the policy information including information on a reference destination that is a basis for selecting the related word.

[0085] (Supplementary Note A8) The policy generation system according to Supplementary Note A6 or A7, wherein the output unit outputs the policy information in a manner in which the policy name and the related word are visually associated with each other.

[0086] (Appendix A9) A policy generation system as described in any of Appendices A1 to A8, further comprising a correction receiving means for receiving a correction instruction from a user including a word for correcting the policy information, and the policy information generation unit corrects the policy information based on the correction instruction.

[0087] (Appendix B1) A policy generation method in which a computer receives business information indicating the status of a target business, receives goals for the target business set by a user as text information, searches for related information in a specified network based on a comparison between the business information and the goals, generates policy information based on the results of the search, and outputs the policy information to the user.

[0088] (Appendix C1) A policy generation program that causes a computer to perform the following processes: accepting business information indicating the status of a target business; accepting goals for the target business set by a user as text information; searching for related information in a specified network based on a comparison between the business information and the goals, and generating policy information according to the results of the search; and outputting the policy information to a user.

[0089] Some or all of the elements (e.g., configurations and functions) described in Appendix A2 to A9 that are dependent on Appendix A1 may also be dependent on Appendix B1 and Appendix C1 in the same dependency relationship as Appendix A2 to A9. Some or all of the elements described in any appendix may be applied to various hardware, software, recording means for recording software, systems, and methods.

[0090] This application claims priority based on Japanese Patent Application No. 2024-32785, filed March 5, 2024, the disclosure of which is incorporated herein by reference in its entirety.

[0091] 100 Measure generation device 110 Business information receiving unit 120 Target receiving unit 130 Measure information generation unit 140 Output unit 200 Measure generation system 300 Related information network 310 Large-scale language model 400 Measure generation device 410 Memory 420 Communication unit 430 Storage unit 431 Program 440 Control unit 441 Business information receiving unit 442 Target receiving unit 443 Measure information generation unit 444 Output unit 445 Correction receiving unit 500 Network 600 Service request device 610 Business information database 620 Business information transmitting unit 630 Target transmitting unit 640 Measure information receiving unit 650 Correction instruction transmitting unit 800, 810 to 817, 820 to 823, 830 to 836 Icon 11 Computer 21 Bus 30 Processor 40 Memory 50 Storage device 60 Input / output interface 70 Network interface

Claims

1. A policy generation system comprising: a business information receiving means for receiving business information indicating the status of a target business; a goal receiving means for receiving text information of the target business set by a user; a policy information generating means for searching for related information in a specified network based on a comparison between the business information and the goal, and generating policy information in accordance with the results of the search; and an output means for outputting the policy information to a user.

2. The policy generation system described in claim 1, wherein the policy information generation means accepts the business information as text information, extracts first attribute information from the business information, identifies second attribute information that expands the extracted first attribute information, searches for the identified second attribute information and the related information related to the goal, and generates the policy information for achieving the goal based on the related information.

3. The policy generation system according to claim 1 or 2, wherein the project information receiving means also receives information on the external environment related to the target project.

4. The policy generation system according to claim 1 or 2, wherein the business information receiving means receives the business information including words related to customer attributes of the target business.

5. The policy generation system according to claim 1 or 2, wherein the business information receiving means receives text information summarized using a predetermined large-scale language model as the business information.

6. A policy generation system as described in claim 1 or 2, wherein the policy information generation means generates the policy information including a policy name indicating at least one policy and a plurality of related words that constitute the policy.

7. The policy generation system according to claim 6, wherein the policy information generation means generates the policy information including information on references that are the basis for selecting the related words.

8. The policy generation system according to claim 6, wherein the output means outputs the policy information in a manner in which the policy name and the related words are visually associated with each other.

9. A policy generation system as described in claim 1 or 2, further comprising a correction receiving means for receiving a correction instruction from a user including a word for correcting the policy information, and the policy information generation means corrects the policy information based on the correction instruction.

10. A policy generation method in which a computer receives business information indicating the status of a target business, receives goals for the target business set by a user as text information, searches for related information in a specified network based on a comparison between the business information and the goals, generates policy information based on the results of the search, and outputs the policy information to the user.

11. A policy generation program that causes a computer to perform the following processes: accepting business information indicating the status of a target business; accepting goals for the target business set by a user as text information; searching for related information in a specified network based on a comparison between the business information and the goals, and generating policy information based on the results of the search; and outputting the policy information to a user.

Images