Information processing method, information processing system and program

Abstract

To provide an information processing method, an information processing system and a program for allowing a large-scale language model to output evaluation information.SOLUTION: An information processing method includes acquiring public information of an object person, generating instruction information for requesting an output of evaluation information for evaluating the object person on the basis of the public information from a prescribed point of view, inputting the instruction information in a prescribed large-scale language model, and allowing the prescribed large-scale language model to output the evaluation information.SELECTED DRAWING: Figure 3

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a tool that can easily perform analysis of segments for appropriate marketing activities.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The technology of Patent Document 1 divides the respondents of the questionnaire into segments based on questionnaire information. However, since it is based on questionnaire information, there is room for improvement from the perspective of accuracy.

Means for Solving the Problems

[0005] According to one aspect of the present invention, there is provided an information processing method executed by an information processing system. This information processing method acquires public information of a target person. Generates instruction information for requesting output of evaluation information for evaluating the target person based on the public information from a predetermined perspective. Inputs the instruction information into a predetermined large language model. The predetermined large language model outputs the evaluation information.

Effects of the Invention

[0006] It is possible to obtain information that serves as an appropriate indicator instead of questionnaire information.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Embodiments for Carrying Out the Invention

[0008] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various characteristic matters shown in the following embodiments (including modification examples; the same applies hereinafter) can be combined with each other.

[0009] <Embodiment 1> 1. System Configuration Diagram FIG. 1 is a diagram showing an example of the system configuration of an information processing system 1000. As shown in FIG. 1, the information processing system 1000 includes, as a system configuration, an information processing apparatus 100 and a system that provides the function of a large language model (hereinafter simply referred to as a large language model) 110. The information processing apparatus 100 and the large language model 110 are communicably connected via a network 150. The information processing apparatus 100 is an example of a computer.

[0010] The information processing apparatus 100 executes the processing related to Embodiment 1. Details of the processing of the information processing apparatus 100 will be described using FIGS. 3 and the like described later. The large language model 110 is a natural language processing model trained using a large amount of text data. The large language model 110 of Embodiment 1 is preferably a large language model tuned particularly for chat (dialogue).

[0011] Here, the information processing system described in the claims may be composed of a plurality of devices or may be composed of a single device. When the information processing system described in the claims is composed of a single device, an example of such a device is the information processing apparatus 100. When the information processing system described in the claims is composed of a plurality of devices, examples of the plurality of devices are the information processing apparatus 100 and the large language model 110, etc.

[0012] 2. Hardware Configuration FIG. 2 is a diagram showing an example of the hardware configuration of the information processing apparatus 100. As shown in FIG. 2, the information processing apparatus 100 includes, as a hardware configuration, a control unit 210, a storage unit 220, an input unit 230, an output unit 240, and a communication unit 250.

[0013] The control unit 210 is a CPU (Central Processing Unit) or the like, and controls the entire information processing apparatus 100. The storage unit 220 is any one of an HDD (Hard Disk Drive), a ROM (Read Only Memory), a RAM (Random Access Memory), an SSD (Solid Sate Drive), or any combination thereof, and stores programs and data (for example, acquired public information, a list of prospective customers, etc. described later) used when the control unit 210 executes processing based on the programs. The storage unit 220 is an example of a storage medium. In the specification, it is described that the data used when the control unit 210 executes processing based on the programs is stored in the storage unit 220, but it may be stored in the storage unit of another device communicable with the information processing apparatus 100. That is, the data may be stored in the storage unit of any device as long as the control unit 210 can refer to it. By the control unit 210 executing processing based on the programs stored in the storage unit 220, the functions of the information processing apparatus 100 and the processing of the information processing apparatus 100 in the sequence diagram shown in FIG. 3 described later are realized.

[0014] The input unit 230 is a keyboard, a mouse, etc., and inputs information based on a selection operation and / or an input operation by an operator. The output unit 240 is a display, etc., and displays input information via a screen by an operator and the result of processing by the control unit 210, etc. The communication unit 250 connects the information processing apparatus 100 to the network 150 and controls communication with other apparatuses.

[0015] 3. Information Processing Hereinafter, the information processing of Embodiment 1 will be described.

[0016] (1) Outline of Processing The control unit 210 of the information processing apparatus 100 acquires the public information of the target person. Here, the public information is information publicly disclosed by the target person (company and / or individual), and is either or both of the information of documents or articles regarding the publicly disclosed target person, and the information of images regarding the publicly disclosed target person. When the target person is a company, examples of the public information include either or both of the information of documents or articles within the company's web page (web page), and the information of images within the company's web page. The web page is just an example, and other examples include securities reports, financial statements, etc. Also, the information of images regarding the target person may include a captured image of the web page regarding the target person. That is, the captured image of the company's web page may also be included in the information of images regarding the company that is the target person. The captured image of the web page may be a captured image of the entire corresponding web page, or a captured image of a part of the corresponding web page. When the target person is an individual, the public information includes either or both of the individual's web page, papers, the information of documents or articles included in the information transmitted by the individual through a publicly available SNS (Social Networking Service), and the information of images. When the target person is an individual, the captured image of the individual's web page may also be included in the information of images regarding the individual who is the target person. The control unit 210 generates a prompt. Here, the prompt is a prompt that includes content requesting the output of evaluation information for evaluating the target person based on the public information from a predetermined perspective. Note that the prompt is an example of the instruction information. The control unit 210 inputs the generated prompt into the large language model 110. The large language model 110 is an example of a predetermined large language model. The large language model 110 outputs evaluation information. Through such processing, it is possible to obtain information that serves as an appropriate indicator in place of the questionnaire information, that is, evaluation information. (2) Details of the processing FIG. 3 is a sequence diagram showing an example of information processing in the information processing system 1000. In the example of FIG. 3, as the information processing in the information processing system 1000, the process of generating a list of prospective customers for the products to be sold or the services to be provided will be described by way of example. The products to be sold or the services to be provided are an example of a predetermined product or service. Hereinafter, for the sake of simplicity of explanation, the products to be sold will be described by way of example. When receiving predetermined operation information, in sequence SQ301, the control unit 210 determines a target person based on the attribute information. For example, the control unit 210 determines a target person based on the attribute information of existing customers of the products to be sold. Here, the attribute information of existing customers is information indicating the attributes of existing customers. For the sake of simplicity of explanation, if a company is taken as an example of the target person, the attribute information of existing customers includes, for example, company scale, sales volume, number of employees, etc. The control unit 210 determines a company similar to these based on the company scale, sales volume, number of employees, etc. of existing customers of the products to be sold as the target person.

[0017] In sequence SQ302, the control unit 210 acquires the public information of the target person determined in sequence SQ301. As described above, when the target person is a company, examples of public information include the company's web page, securities report, financial statements, etc. For example, the control unit 210 uses web scraping technology to acquire information such as the target person's web page, securities report published on the web, and financial statements published on the web.

[0018] In sequence SQ303, the control unit 210 determines a predetermined perspective based on the information of the product to be sold. Examples of the information of the product to be sold include, for example, product introduction materials, product sales materials, product brochures, etc. For example, the control unit 210 recognizes the characters described in the product introduction materials, product sales materials, product brochures, etc., extracts the features of the product, and determines a predetermined perspective based on the features of the product. Examples of the predetermined perspective include, for example, "a workplace where it is easy to work", "promoting DX (Digital Transformation)", "enthusiastic about employee training", etc. The predetermined perspective may be one or more.

[0019] As another example of determining a predetermined perspective, the control unit 210 may determine a perspective by using a learned model in which the information of the product to be sold such as product introduction materials, product sales materials, and product brochures is used as input data and the perspective corresponding to the product is used as output data. That is, the control unit 210 inputs the information of the product to be sold such as product introduction materials, product sales materials, and product brochures into the learned model. Then, the control unit 210 may determine the perspective output from the learned model as the perspective of the product to be sold. The same applies to the case of services if the product is read as a service.

[0020] Note that the process of sequence SQ303 may be simultaneous with sequence SQ301 or sequence SQ302, or may be before sequence SQ301 or sequence SQ302.

[0021] In sequence SQ304, the control unit 210 generates a prompt based on the perspective determined in sequence SQ303, the subject selected in sequence SQ301, and the public information acquired in sequence SQ302. More specifically, the control unit 210 generates a prompt that requests the output of evaluation information for evaluating the subject selected in sequence SQ301 from the perspective determined in sequence SQ303 based on the public information acquired in sequence SQ302. The control unit 210 may include information specifying the output format of the evaluation information in the prompt. This is because it is more convenient to use the output evaluation information when the output format is a predetermined output format. Also, the control unit 210 may include examples of input and output in the prompt to improve the accuracy of the output. Further, when the public information is text information, the control unit 210 may include in the prompt information instructing to evaluate the subject for each piece of text information of a predetermined number of characters, or when the public information is image information, the control unit 210 may include in the prompt information instructing to evaluate the subject for each piece of image information (for example, an image included in a web page).

[0022] In sequence SQ305, the control unit 210 inputs the prompt generated in sequence SQ304 to the large language model 110. For example, the control unit 210 inputs the prompt to the large language model 110 using an API (Application Programming Interface).

[0023] In sequence SQ306, the control unit 210 receives the evaluation information output by the large language model 110 via the API. As the evaluation information, for example, there is information indicating how many points out of 100 for each predetermined perspective. For example, when the perspectives are "easy-to-work workplace", "promoting DX", and "enthusiastic about employee training", the control unit 210 receives as the evaluation information "easy-to-work workplace" 80 points, "promoting DX" 65 points, "enthusiastic about employee training" 85 points, etc.

[0024] In sequence SQ307, the control unit 210 determines whether the target person meets a predetermined requirement based on the received evaluation information. If the control unit 210 determines based on the evaluation information that the target person meets the predetermined requirement, it proceeds to sequence SQ308. If the control unit 210 determines based on the evaluation information that the target person does not meet the predetermined requirement, it ends the information processing. For example, when the predetermined requirement is "being 70 points or more in all aspects", and the evaluation information received from the large language model 110 is 80 points for "easy-to-work workplace", 65 points for "promoting DX", 85 points for "enthusiastic about employee training", etc., the control unit 210 determines that the target person does not meet the predetermined requirement. When the predetermined requirement is "being 70 points or more in all aspects", and the evaluation information received from the large language model 110 is 80 points for "easy-to-work workplace", 95 points for "promoting DX", 85 points for "enthusiastic about employee training", etc., the control unit 210 determines that the target person meets the predetermined requirement.

[0025] In sequence SQ308, the control unit 210 adds the target person to the list of customer candidates for the product to be sold. Figure 4 is a diagram showing an example of the list of customer candidates. The list 400 is the list of customer candidates. The list contains the information of the target person as a customer candidate. In the example of Figure 4, the company name, address, phone number, and email address are included as the target person. For example, when the creation of the list 400 is completed, the control unit 210 sends a sales email for the product to be sold to the target person included in the list 400.

[0026] According to the processing of Embodiment 1, it is possible to obtain information that is an appropriate indicator instead of the questionnaire information, that is, the evaluation information. Also, when the evaluation information meets the predetermined requirement, the target person can be added to the list. In the example of the above-described embodiment, the list of customer candidates for the product can be created promptly and based on an appropriate indicator.

[0027] In addition, in the first embodiment, the description was given using the example of creating a list of customer candidates, but the present invention is not limited to this. For example, if the target person is an applicant for company employment and the qualitative information indicating the company's values derived from the company's homepage or pamphlet is used as a predetermined perspective, etc., the control unit 210 generates instruction information for requesting the output of evaluation information for evaluating the applicant based on the applicant's public information and information indicating the company's values, etc., and can input it into the large language model. Then, the control unit 210 can receive the applicant's evaluation information from the large language model.

[0028] (Modification Example 1) A modification example 1 of the first embodiment will be described. Note that the modification example is included in the first embodiment and does not represent other embodiments. The same applies to the following modification examples. In modification example 1, the points different from the first embodiment will be mainly described. In the first embodiment, the large language model 110 was provided as a separate entity from the information processing apparatus 100. However, the large language model 110 may be implemented in the information processing apparatus 100. Even with the configuration of modification example 1, the same effects as those of the first embodiment can be achieved.

[0029] (Modification Example 2) A modification example 2 of the first embodiment will be described. In modification example 2, the points different from the first embodiment will be mainly described. In the first embodiment, the description was given using the large language model as an example. However, a learned model specifically trained instead of the large language model may be used. Even with the configuration of modification example 2, the same effects as those of the first embodiment can be achieved.

[0030] (Modification Example 3) A modification example 3 of the first embodiment will be described. In modification example 3, the points different from the first embodiment will be mainly described. In Embodiment 1, a series of processes including input of a prompt, acquisition of output results, determination, and addition of a list of candidates were performed. The control unit 210 of Modification 3 may perform this series of processes a plurality of times and update the list of candidates based on the results. Furthermore, when performing this series of processes a plurality of times, the control unit 210 of Modification 3 may obtain output results by using, for example, a paraphrased expression of the prompt each time. Even with the configuration of Modification 3, the same effects as those of Embodiment 1 can be achieved, and a highly accurate list of candidates can be obtained even when the output from the learned model is unstable.

[0031] Finally, although various embodiments according to the present invention have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. The embodiments and their modifications are included in the scope and gist of the invention and are included in the invention described in the claims and its equivalent scope.

Explanation of Reference Numerals

[0032] 100: Information processing apparatus 110: Large language model 150: Network 210: Control unit 220: Storage unit 230: Input unit 240: Output unit 250: Communication unit 400: List 1000: Information processing system

Claims

1. An information processing method executed by an information processing system, comprising: acquiring public information of a target person; generating instruction information for requesting output of evaluation information for evaluating the target person based on the public information from a predetermined perspective; inputting the instruction information into a predetermined large language model; wherein the predetermined large language model outputs the evaluation information. An information processing method.

2. The information processing method according to Claim 1, wherein when it is determined based on the output evaluation information that the target person meets a predetermined requirement, adding the target person to a list of candidates. An information processing method.

3. The information processing method according to Claim 1, wherein determining the target person based on attribute information; acquiring the public information of the determined target person. An information processing method.

4. The information processing method according to Claim 1, wherein determining the target person based on attribute information of existing customers of a predetermined product or service; acquiring the public information of the determined target person. An information processing method.

5. The information processing method according to Claim 1, wherein determining the predetermined perspective based on information of a predetermined product or service; generating instruction information for requesting output of evaluation information for evaluating the target person from the determined predetermined perspective based on the public information. An information processing method.

6. The information processing method according to Claim 1, wherein the public information is either or both of document or text information about the publicly available target person and image information about the publicly available target person. An information processing method.

7. The information processing method according to Claim 6, wherein the image information about the target person includes a captured image of a web page related to the target person. An information processing method.

8. The information processing method according to Claim 1, wherein the instruction information includes information specifying an output format of the evaluation information. An information processing method.

9. An information processing system, comprising: at least one or more control units, wherein the control unit: acquires public information of a target person; generates instruction information for requesting output of evaluation information for evaluating the target person based on the public information from a predetermined perspective; inputs the instruction information into a predetermined large language model; wherein the predetermined large language model outputs the evaluation information. An information processing system.

10. A program for causing a computer to execute the information processing method according to any one of Claims 1 to 8. ​ ​

Images