Information processing device, trained model, information processing method, and program

Abstract

The purpose of the present invention is to provide an information processing device which makes it possible to suitably evaluate work performance ability. An information processing device according to the present disclosure comprises: an attribute information reception unit which receives personal attribute information; a value estimation unit which uses a trained model and estimates the value of work performance ability included in the attribute information on the basis of the personal attribute information; and a value output unit which outputs the estimated value information that indicates the estimated value. The trained model has been trained by applying, as training data, demand information pertaining to a demand for the work performance ability, supply information pertaining to a supply of the work performance ability, relevant information which can affect at least one among the demand and the supply, and value information that indicates the value of the work performance ability.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, a learned model, an information processing method, and a program.

Background Art

[0002] In the labor market, the market value of a worker's job performance ability (e.g., skills and knowledge) changes with the times. Therefore, it is desired to appropriately evaluate the market value of a worker's individual job performance ability according to the times.

[0003] As a related technique, Patent Document 1 discloses a social simulation system for predicting or calculating the dynamics of society or the market. When matching between an employer agent and a worker agent is established in the simulation world, the system confirms the evaluations made by both parties to each other. If the evaluations of each other are high, the system presents information to the employer and the worker and takes measures to bring the two together in the real world.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] A worker can increase their market value by improving their job performance ability. Also, by making the worker aware of the market value of their job performance ability, the worker's motivation to improve their job performance ability can be increased. However, it is difficult to quantitatively evaluate the market value of a worker's job performance ability. [[ID=4!]]

[0006] The purpose of this disclosure is to provide an information processing device, a trained model, an information processing method, and a program that can appropriately evaluate work performance capabilities, in light of the issues described above. [Means for solving the problem]

[0007] The information processing device relating to this disclosure is An attribute information receiving unit that receives personal attribute information, A value estimation unit estimates the value of the work performance capabilities included in the attribute information by using a trained model that has been trained using the following as training data: demand information regarding the demand for work performance capabilities, supply information regarding the supply of work performance capabilities, related information that may influence at least one of the demand and the supply, and value information indicating the value of the work performance capabilities, based on the individual attribute information received by the attribute information receiving unit. The system includes a value output unit that outputs estimated value information indicating the value estimated by the value estimation unit.

[0008] The trained model relating to this disclosure is An input layer that accepts input of demand information relating to the demand for work performance capabilities, supply information relating to the supply of said work performance capabilities, and related information that may influence at least one of said demand and said supply, The system includes an output layer that estimates and outputs the value of the business execution capability corresponding to the demand information, the supply information, and the related information, The computer is configured to input the job performance capabilities included in an individual's attribute information into the input layer and to output the estimated value from the output layer.

[0009] The information processing method relating to this disclosure is: An attribute information reception step that receives personal attribute information, A value estimation step is performed using a trained model that has been trained with the following as training data: demand information regarding the demand for work performance capabilities, supply information regarding the supply of the work performance capabilities, related information that may influence at least one of the demand and the supply, and value information indicating the value of the work performance capabilities, based on the individual's attribute information received in the attribute information reception step; The system includes a value output step that outputs estimated value information showing the value estimated in the value estimation step.

[0010] The program related to this disclosure is An attribute information reception step that receives personal attribute information, A value estimation step is performed using a trained model that has been trained with the following as training data: demand information regarding the demand for work performance capabilities, supply information regarding the supply of the work performance capabilities, related information that may influence at least one of the demand and the supply, and value information indicating the value of the work performance capabilities, based on the individual's attribute information received in the attribute information reception step; The computer is instructed to perform a value output step, which outputs estimated value information showing the value estimated in the value estimation step, and [Effects of the Invention]

[0011] The information processing device, trained model, information processing method, and program described herein can appropriately evaluate the ability to perform tasks. [Brief explanation of the drawing]

[0012] [Figure 1] This is a block diagram showing the configuration of the information processing device related to this disclosure. [Figure 2] This flowchart shows the processing performed by the information processing device related to this disclosure. [Figure 3] This block diagram shows the configuration of the information processing system related to this disclosure. [Figure 4]It is a block diagram showing the configuration of an information processing apparatus according to the present disclosure. [Figure 5] It is a diagram showing an example of teacher data according to the present disclosure. [Figure 6] It is a diagram showing an example of a learned model according to the present disclosure. [Figure 7] It is a diagram showing a specific example of weighting according to the present disclosure. [Figure 8] It is a flowchart showing the processing performed by the information processing apparatus according to the present disclosure. [Figure 9] It is a diagram showing an example of display information for displaying estimated value information according to the present disclosure. [Figure 10] It is a block diagram exemplifying the hardware configuration of a computer that realizes the information processing apparatus according to the present disclosure.

Mode for Carrying Out the Invention

[0013] 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 denoted by the same reference numerals. For the sake of clarity of explanation, duplicate explanations are omitted as necessary.

[0014] <Embodiment 1> First, referring to FIG. 1, the configuration of an information processing apparatus 100 according to the present disclosure will be described. FIG. 1 is a block diagram showing the configuration of the information processing apparatus 100. The information processing apparatus 100 includes an attribute information reception unit 101, a value estimation unit 102, and a value output unit 103.

[0015] The attribute information reception unit 101 receives personal attribute information. The value estimation unit 102 estimates the value of the business execution ability included in the attribute information using a learned model based on the personal attribute information received by the attribute information reception unit 101.

[0016] The trained model is trained using demand information regarding the demand for job performance capabilities, supply information regarding the supply of job performance capabilities, related information that may influence at least one of demand and / or supply, and value information indicating the value of job performance capabilities as training data.

[0017] The value output unit 103 outputs estimated value information that shows the value estimated by the value estimation unit 102.

[0018] The information processing device 100 includes a processor, memory, and storage device (not shown). The storage device stores a computer program on which the processing described herein is implemented. The processor can load the computer program from the storage device into memory and execute the computer program. In this way, the processor realizes the functions of the attribute information receiving unit 101, the value estimation unit 102, and the value output unit 103.

[0019] Next, we will explain the processes performed by the information processing device 100 with reference to Figure 2. Figure 2 is a flowchart showing the processes performed by the information processing device 100.

[0020] First, the attribute information receiving unit 101 receives an individual's attribute information (S101). Next, the value estimation unit 102 uses a trained model to estimate the value of the work performance capabilities included in the attribute information based on the received individual's attribute information (S102). Finally, the value output unit 103 outputs estimated value information indicating the estimated value (S103).

[0021] With this configuration, the information processing device 100 described herein can appropriately evaluate the ability to perform tasks.

[0022] <Embodiment 2> Next, Embodiment 2 will be described with reference to Figures 3 to 10. Embodiment 2 is a specific example of Embodiment 1 described above.

[0023] (Configuration of Information Processing System 1) First, the configuration of the information processing system 1 according to this disclosure will be described with reference to Figure 3. Figure 3 is a block diagram showing the configuration of the information processing system 1. As shown in the figure, the information processing system 1 comprises an information processing device 10, a personal user terminal 20, and a corporate user terminal 30. The information processing system 1 may comprise multiple personal user terminals 20 and multiple corporate user terminals 30.

[0024] The information processing device 10, the personal user terminal 20, and the corporate user terminal 30 are connected to each other via a network N. Network N is a wired or wireless communication line. Network N may be, for example, the internet, a dedicated line, a telephone line, a mobile communication network, or other communication lines. Network N may also be a combination of these.

[0025] Information processing device 10 is an example of the information processing device 100 described above. Information processing device 10 is an information processing device that can estimate and output the value of an individual's work performance ability by performing predetermined information processing.

[0026] Job performance ability refers to the ability to perform a job. Job performance ability may include skills such as the techniques or skills required to perform a specific job. Examples of skills include abilities related to translation, programming, management, clerical work, accounting, sales, or marketing. These are just examples; various skills can be included in job performance ability.

[0027] Furthermore, job performance capabilities may include knowledge, education, qualifications, usable tools, or proficiency in those tools related to the job. Job performance capabilities may also be associated with industry, job type, etc. An individual's job performance capabilities may include multiple skills and knowledge.

[0028] The personal user terminal 20 is a terminal used by an individual user. The corporate user terminal 30 is a terminal used by a corporate user.

[0029] Here, an individual user represents a person who possesses the ability to perform tasks whose value is to be estimated. An individual user can use the individual user terminal 20 to estimate the value of their own ability to perform tasks and obtain the estimated value (hereinafter sometimes referred to as the estimated value). This allows the individual user to understand the estimated value of their own ability to perform tasks, for example, when looking for a job or changing jobs.

[0030] Furthermore, corporate users indicate individuals who use the information processing system 1 as recruiters to contact individual users. Corporate users use the corporate user terminal 30 to obtain an estimated value of the individual user's work performance capabilities. This allows corporate users to utilize the obtained estimated value, for example, in recruitment activities.

[0031] The personal user terminal 20 and the corporate user terminal 30 may be, for example, a PC (Personal Computer), a tablet terminal, or a smartphone. The personal user terminal 20 and the corporate user terminal 30 send and receive data to and from the information processing device 10 via the network N.

[0032] The personal user terminal 20 and the corporate user terminal 30 are equipped with input units (not shown) that accept information input from their respective users. The input units of the personal user terminal 20 and the corporate user terminal 30 are, for example, input devices such as keyboards.

[0033] Furthermore, the individual user terminal 20 and the corporate user terminal 30 are equipped with output units (not shown) that output information to their respective users. The output units of the individual user terminal 20 and the corporate user terminal 30 are, for example, display devices such as displays.

[0034] The personal user terminal 20 and the corporate user terminal 30 may be configured to include an input / output unit equipped with input and output functions. The input / output unit may be, for example, a touch panel display that allows input operations to be performed by touching it with a finger.

[0035] (Overview of the processes performed by Information Processing System 1) Here, we will explain the overview of the processing in the information processing system 1. The input unit of the personal user terminal 20 receives attribute information from the personal user. Here, attribute information is information that indicates the attributes of the personal user. Attribute information includes information about the personal user's ability to perform work. Therefore, attribute information may include, for example, information such as the personal user's skills, knowledge, industry, or occupation, which represent their ability to perform work.

[0036] Furthermore, attribute information may include information other than job performance capabilities. Attribute information may include, for example, the number of job changes, educational background, previous salary, or desired working conditions (e.g., working hours, employment contract, or work location).

[0037] Individual users register information including these attribute details with the information processing device 10 using their personal user terminal 20. Individual users can input attribute information using, for example, an input form screen for registering a resume. In this way, the information processing device 10 receives the individual user's attribute information from the personal user terminal 20.

[0038] The information processing device 10 estimates the value of the business performance capabilities contained in the received attribute information by performing predetermined processing using a trained model. The trained model can be stored in the information processing device 10.

[0039] The trained model is pre-trained using demand information, supply information, related information, and value information as training data. Demand information is information about the demand for job performance capabilities. Demand information can be obtained based on multiple job postings. Supply information is information about the supply of job performance capabilities. Supply information can be obtained based on the attribute information of multiple individuals.

[0040] Relevant information is information that can influence at least one of supply and demand. Relevant information may include, for example, information on tools that can replace work performance capabilities or information on global affairs. Relevant information can be obtained from sources such as information posted on social networking services (SNS) or news websites.

[0041] Value information is information that indicates the value of job performance capabilities. Value information is related to demand information, supply information, and related information. For example, the value of a certain job performance capability A changes depending on the balance of supply and demand for job performance capability A, and the availability of tools that can substitute for job performance capability A. Value information can be obtained based on the attribute information of multiple individuals, etc.

[0042] The information processing device 10 outputs estimated value information that shows the value estimated using a trained model. The estimated value information may be represented, for example, by a score (numerical value) or compensation (amount of money) that shows the estimated value of job performance ability. The estimated value information may also be represented by an estimated annual income. Alternatively, the estimated value information may be represented by a score that shows the balance between supply and demand for job performance ability.

[0043] The information processing device 10 may, for example, output estimated value information to an individual user terminal 20. This allows the individual user to recognize the estimated value corresponding to their own work performance capabilities. The information processing device 10 may also output estimated value information to a corporate user terminal 30. This allows the corporate user to understand the estimated value corresponding to the individual user's work performance capabilities.

[0044] (Configuration of the information processing device 10) Next, the configuration of the information processing device 10 will be described with reference to Figure 4. Figure 4 is a block diagram showing the configuration of the information processing device 10. The information processing device 10 includes an attribute information receiving unit 11, a value estimation unit 12, a value output unit 13, a learning unit 14, a weight setting unit 15, and a storage unit 19.

[0045] The attribute information receiving unit 11 is an example of the attribute information receiving unit 101 described above. The attribute information receiving unit 11 receives attribute information of individual users. For example, the attribute information receiving unit 11 displays an input form screen for registering a resume on the individual user terminal 20 and accepts input into the input form.

[0046] Attribute information includes information about job performance capabilities. This information may include an individual user's skills, knowledge, industry, job title, qualifications, usable tools, or proficiency with those tools. Attribute information may also include information other than job performance capabilities. This information may include, for example, the number of job changes, educational background, previous salary, or desired working conditions.

[0047] The value estimation unit 12 is an example of the value estimation unit 102 described above. Based on the individual's attribute information received by the attribute information receiving unit 11, the value estimation unit 12 uses a trained model to estimate the value of the work performance capabilities included in the attribute information.

[0048] If job performance ability includes multiple skills, the value estimation unit 12 may estimate the value of the job performance ability as a whole, or it may estimate the value of each of the skills. The value estimation unit 12 can represent the estimated value using, for example, a score or compensation. The value estimation unit 12 may also estimate the balance between supply and demand for job performance ability and represent this balance with a score or the like.

[0049] For example, suppose an individual user possesses a work performance ability A that includes skills a1, a2, and a3. In this case, the value estimation unit 12 can estimate the value corresponding to each of skills a1 to a3 and represent the estimated value using the score or compensation corresponding to each skill. In this way, the value estimation unit 12 can estimate the value of each skill possessed by the individual user. The value estimation unit 12 may also, for example, divide skills a1 to a3 into groups and estimate the value for each group.

[0050] The value estimation unit 12 may also estimate the value corresponding to the entire job performance ability A (skills a1 to a3) and express the estimated value using the score or compensation corresponding to job performance ability A. In this case, the value estimation unit 12 may express the annual income of an individual user with job performance ability A as the estimated value.

[0051] The value estimation unit 12 estimates the value of work performance capabilities using a pre-trained model 195 stored in the memory unit 19. The pre-trained model 195 is pre-trained using demand information 191, supply information 192, related information 193, and value information 194 stored in the memory unit 19 as training data. Details of the pre-trained model 195 will be described later.

[0052] The value output unit 13 is an example of the value output unit 103 described above. The value output unit 13 outputs estimated value information that shows the value estimated by the value estimation unit 12. The value output unit 13 may output the estimated value information to the personal user terminal 20 or the corporate user terminal 30, or to an output unit (not shown) provided in the information processing device 10. The estimated value information may be, for example, display information for displaying the estimated value using characters or images.

[0053] The learning unit 14 trains the pre-trained model 195. The learning unit 14 generates the pre-trained model 195 by training it using demand information 191, supply information 192, related information 193, and value information 194 as training data.

[0054] Now, let's refer to Figure 5 to explain the training data used for learning. Figure 5 shows an example of training data.

[0055] As shown by the solid lines in the diagram, demand information 191, supply information 192, related information 193, and value information 194 are related to each other. For example, demand information 191 and supply information 192 may influence value information 194. Also, related information 193 may influence at least one of demand information 191 and supply information 192. Note that the solid lines shown in the diagram are just one example of the relationships between the information and do not exclude relationships other than those shown. For example, related information 193 and value information 194 may be related.

[0056] Furthermore, W shown in the figure represents the weight associated with each piece of information. The weight W can be set automatically or manually in the weight setting unit 15, which will be described later. The learning unit 14 uses the set weight W to train the trained model 195.

[0057] Furthermore, the diagram shows examples of related information 193, including information on alternative tools (alternative methods), startups, the industry, global trends, industry white papers, and annual reports. These are just examples, and other information may be used as related information 193.

[0058] The learning unit 14 acquires information to be used as training data via a network N or the like. For example, the learning unit 14 acquires demand information 191 based on multiple job postings acquired from multiple corporate user terminals 30 and job posting websites. The learning unit 14 also acquires supply information 192 based on attribute information of multiple individuals registered via multiple individual user terminals 20 or the like.

[0059] Furthermore, the learning unit 14 acquires information on alternative tools, startups, industries, global affairs, industry white papers, or annual reports as related information 193 via the network N, etc.

[0060] Alternative tools refer to alternative means of performing tasks. Examples of alternative tools include applications using AI (Artificial Intelligence). Startups, on the other hand, refer to information about startup companies and their technologies.

[0061] The learning unit 14 acquires text information, for example, posted on social media, and based on that text information, it acquires related information 193 regarding alternative tools and startups. Specifically, the learning unit 14 performs natural language processing on the text information acquired from social media, etc. Through this, the learning unit 14 extracts the meaning contained in the text information. The meaning contained in the text information may include, for example, information on evaluations of alternative tools.

[0062] The learning unit 14 trains the trained model 195 based on the acquired information so that the value of the ability to perform the job decreases as at least one of the quality and quantity of the alternative tools increases. For example, suppose the alternative tool is a translation tool. The learning unit 14 extracts positive posts about translation tools from social media, such as "The accuracy of translation tool T1 has improved" and "Translation tool T2 is easy to use."

[0063] The learning unit 14 determines, based on the extracted posts, whether at least one of the quality and quantity of translation tools has increased. If the learning unit 14 determines that either one has increased, it trains the pre-trained model 195 so that the value of an individual's translation skills decreases. The learning unit 14 may also extract the product names of translation tools and determine the change in the quantity of translation tools. Alternatively, the learning unit 14 may train the pre-trained model 195 so that the value of job performance ability increases as at least one of the quality and quantity of alternative tools decreases.

[0064] In this way, the learning unit 14 can extract the meaning contained in posts about alternative tools and use the extraction results to train the pre-trained model 195. This allows the learning unit 14 to train the pre-trained model 195 so that the value of skills decreases as human tasks are replaced by AI.

[0065] Furthermore, it is conceivable that the market may expand as the number of alternative tools increases, leading to greater demand for the ability to perform tasks. The learning unit 14 may adjust the value of alternative tools as appropriate, taking into account their relationship with other information and in accordance with market trends, to train the pre-trained model 195. In addition, the learning unit 14 may extract the meaning of information not only from text information but also from image information by performing natural language processing on it.

[0066] The learning unit 14 similarly extracts the meaning contained in information related to startups and uses the information that affects the value of business performance capabilities to train the trained model 195.

[0067] The learning unit 14 may obtain relevant information 193 from other media, not just social networking services (SNS). For example, the learning unit 14 may obtain information regarding trends in the industry to which the corporate user (employer) belongs as relevant information 193. Information regarding industry trends is, for example, information contained in publications issued by the corporate user or the industry to which the corporate user belongs. The learning unit 14 extracts from such publications information that may influence at least one of the supply and demand for job performance capabilities. Publications include annual reports issued by the corporate user or industry white papers issued in the industry to which the corporate user belongs.

[0068] Continuing with Figure 5, we will now explain the value information 194. Value information 194 is information that indicates the value of work performance ability. The learning unit 14 calculates the value corresponding to the demand information 191, supply information 192, and related information 193, and stores it in the storage unit 19 as value information 194. Value information 194 may be represented, for example, by a score or compensation that indicates the value of work performance ability. Value information 194 may also be represented by annual income.

[0069] The learning unit 14 associates the demand information 191, supply information 192, related information 193, and value information 194 acquired at predetermined timings and stores them in the storage unit 19. For example, the learning unit 14 stores the individual user's work performance ability at a predetermined timing and the value corresponding to that work performance ability (for example, the individual user's annual income) as value information 194, associating it with the demand information 191, supply information 192, and related information 193 at that timing. The learning unit 14 may, for example, acquire the annual income corresponding to the work performance ability by extracting information such as basic salary from job postings.

[0070] The learning unit 14 acquires demand information 191, supply information 192, related information 193, and value information 194 as described above, and stores them as training data. By performing training using the training data, the learning unit 14 can generate a trained model 195 that estimates the value corresponding to unknown work performance capabilities.

[0071] The learning unit 14 may estimate future market value based on demand information 191, supply information 192, and related information 193 at multiple different time periods, and use the estimated market value to train the trained model 195. Here, "future" refers to a time when a predetermined period has elapsed from the present. The learning unit 14 can set the predetermined period in advance. This allows the trained model 195 to learn based on the estimated future market value.

[0072] The learning unit 14 stores, for example, demand information 191, supply information 192, and related information 193, associating them with the acquisition date and time, update date and time, etc. of each piece of information. This allows the learning unit 14 to use information from multiple different time periods for learning purposes.

[0073] For example, the learning unit 14 compares past job postings with current job postings. Based on the comparison results, the learning unit 14 determines the changes in the value of job performance capabilities. Based on these changes in value, the learning unit 14 estimates the future market value after a predetermined period has elapsed. The learning unit 14 trains the trained model 195 to perform learning using the estimated market value. In this way, the trained model 195 can output estimation results that take into account the decline in the value of job performance capabilities due to the passage of time and changes in global circumstances, based on information acquired at different times.

[0074] Furthermore, the learning unit 14 may train the trained model 195 by setting an expiration date for the work performance capabilities. The expiration date for the work performance capabilities indicates the time when the current value of the work performance capabilities is expected to fall below a predetermined value.

[0075] The value of job performance ability can be specifically estimated using multiple regression analysis. In multiple regression analysis, if the value to be estimated is the dependent variable Y, then the dependent variable Y can be expressed by the following formula using the independent variables X1, X2, X3, ... and the partial regression coefficients b1, b2, b3, ....

[0076] [Mathematics 1] Y=b1X1+b2X2+b3X3+···+b0 (1)

[0077] Here, the dependent variable Y is the estimated value of an individual user's ability to perform tasks. X1, X2, X3, ... represent the information shown in Figure 5, specifically the demand information 191, supply information 192, and related information 193. The partial regression coefficients b1, b2, b3, ... correspond to the weights W mentioned above. Note that b0 indicates the bias.

[0078] The dependent variable Y may be, for example, a score for job performance ability or compensation. If job performance ability includes multiple skills, the dependent variable Y may be the value of some of those skills or the value of the entire job performance ability. For example, the dependent variable Y may be the compensation for the entire job performance ability (e.g., annual salary). Furthermore, the dependent variable Y may be the quantity demanded, indicating the magnitude of demand, or the quantity supplied, indicating the magnitude of supply. In addition, the dependent variable Y may be information indicating the balance between supply and demand.

[0079] The explanatory variables X1, X2, X3, ... are scores based on information about job postings, attribute information, alternative tools, startups, industries, global trends, industry white papers, and annual reports, as shown in Figure 5. In other words, the score based on job postings can be denoted as X1, the score based on attribute information as X2, the score based on alternative tools as X3, ...

[0080] For example, suppose we want to estimate the value of translation skills. The score X1 based on job postings is obtained from all job postings of companies. For example, the learning unit 14 sets X1=10 when there is a high demand for translation skills and X1=5 when there is a low demand. The learning unit 14 may determine whether there is a high or low demand using a predetermined threshold. The threshold can be changed as appropriate. The same applies to other explanatory variables.

[0081] Furthermore, the attribute-based score X2 is calculated from the entire attribute information of the job seeker. For example, the learning unit 14 sets X2 = -10 when there is a large supply of translation skills and X2 = -5 when there is a small supply. X1 and X2 may also be set based on the recruitment period and acceptance rate of the skills. For example, the learning unit 14 sets X1 and X2 so that the longer the recruitment period, the greater the demand is compared to the supply. Also, the learning unit 14 sets X1 and X2 so that the higher the acceptance rate, the greater the demand is compared to the supply.

[0082] The score X3, based on information about alternative tools, is determined based on information extracted using natural language processing from sources such as social media. For example, the learning unit 14 sets X3 = -20 if posts about alternative tools are favorable or if there are many such posts. The learning unit 14 also sets X3 = 0 if posts about alternative tools are unfavorable or if there are few such posts. The learning unit 14 may also set X3 based on the scarcity of alternative tools (e.g., price or adoption rate) or the rate of substitution.

[0083] The learning unit 14 can similarly set scores X4 to X8 based on information about startups, industries, global affairs, industry white papers, and annual reports. The learning unit 14 adjusts coefficients b1 to b8 multiplied by X1 to X8 to train the trained model 195 to output appropriate estimation results.

[0084] Here, we will describe the trained model 195 with reference to Figure 6. Figure 6 is a diagram showing an example of the trained model 195. The trained model 195 is a neural network that takes demand information 191, supply information 192, and related information 193 as inputs and outputs value information 194. The neural network may be, for example, a CNN (Convolutional Neural Network).

[0085] As shown in the figure, the trained model 195 has a multilayer structure consisting of, for example, an input layer L1, a hidden layer L2, and an output layer L3. In the figure, the neuronal elements in each layer are shown as circles, and the transmission elements connecting each layer are shown as solid arrows. The transmission elements have weighted values ​​to transmit the state of the neuronal elements from the input layer L1 to the output layer L3. The information input to the input layer L1 and the information output from the output layer L3 are shown as dashed lines.

[0086] As shown in the figure, the input layer L1 has nerve cell elements that receive inputs of demand information 191, supply information 192, and related information 193. The intermediate layer L2 has nerve cell elements that receive the output from the input layer L1, and each nerve cell element is connected to the nerve cell elements of the input layer L1 via a transmission element.

[0087] The intermediate layer L2 uses machine learning to determine the parameters used in the computational process of extracting features from the demand information 191, supply information 192, and related information 193, based on the training data of demand information 191, supply information 192, related information 193, and value information 194. A well-known algorithm may be used for machine learning.

[0088] The output layer L3 has nerve cell elements that receive the output from the hidden layer L2, and each nerve cell element is connected to the nerve cell elements of the hidden layer L2 via a transmission element. Based on the calculation results in the hidden layer L2, the output layer L3 estimates the value of the work performance capabilities contained in the attribute information input to the input layer L1, and outputs value information.

[0089] When an unknown task performance capability is input to the trained model 195, it outputs a value estimated from that unknown task performance capability. The trained model 195 uses the difference between the value information 194 and the estimated value as its error, and learns to minimize this error. For example, the trained model 195 is constructed to minimize this error.

[0090] In this way, the trained model 195 can make the computer function by inputting the job performance capabilities contained in the individual's attribute information into the input layer and outputting the estimated value from the output layer. Note that the example shown in Figure 6 is just one example, and the configuration of the trained model 195 is not limited to what is shown. For example, the hidden layer L2 may be configured in a multi-layer structure. Also, the trained model 195 may be constructed using methods other than neural networks.

[0091] Returning to Figure 4, the explanation continues. The weight setting unit 15 sets weights for at least one of the demand information, supply information, and related information. The weight setting unit 15 can perform weighting automatically using well-known techniques. For example, the weight setting unit 15 determines weights based on the combination of industry and occupation.

[0092] Figure 7 shows a specific example of weighting. In the figure, the magnitude of the weight is shown in three levels: large, medium, and small. In the figure, one of the three levels is set for each of the demand information, supply information, and related information. The magnitude of the weight may be set in four or more levels, or in two levels. The magnitude of the weight may also be set numerically.

[0093] The weight setting unit 15, for example, refers to a table (not shown) containing the information shown in the figure, and obtains a weight level corresponding to the industry or occupation. The weight setting unit 15 sets the weights for demand information, supply information, and related information, respectively, according to the obtained level.

[0094] For example, the value of the work performance capabilities of an individual in occupation G, as shown in Example 7, is relatively strongly correlated with demand information, supply information, and related information. Therefore, the weight setting unit 15 sets a "large" weight for all of the demand information, supply information, and related information. Occupation G is, for example, an engineer who works with the latest technology.

[0095] On the other hand, the value of the work performance capabilities possessed by individuals in occupation D as shown in Example 4 and individuals in occupation J as shown in Example 10 has a relatively weak correlation with demand information, supply information, and related information. Therefore, the weight setting unit 15 sets a "small" weight for all of the demand information, supply information, and related information.

[0096] In this way, the weight setting unit 15 can automatically assign weights according to the industry or job type.

[0097] The weight setting unit 15 may also accept input from the setter and set the weights accordingly. The setter is, for example, a corporate user using the corporate user terminal 30. This allows the weight setting unit 15 to manually adjust the weights.

[0098] For example, the weight setting unit 15 first automatically assigns weights. Next, the weight setting unit 15 accepts input from the user and modifies the weights. The weight setting unit 15 then retrains the trained model 195 using the modified weights. In this way, the weight setting unit 15 can train the trained model 195 so that it can accurately estimate the value of work performance ability. Furthermore, in this way, if there is a discrepancy between the estimation result using the automatically set weights and the actual value, the user can manually adjust the weights to reduce the discrepancy.

[0099] Furthermore, the setter can change the weighting of only some of the factors, such as X1, X2, X3, ..., X8, allowing for flexible weighting settings. This enables, for example, the rapid reflection of any impact on the estimation results in the event of an event that could significantly affect the demand or supply of work capacity.

[0100] The order of weighting is not limited to that described above. The weight setting unit 15 may first manually assign weights according to the user's input, and then automatically assign weights. Furthermore, the weight setting unit 15 may perform automatic or manual weighting multiple times.

[0101] The weight setting unit 15 may divide X1, X2, X3, ..., X8 into multiple groups and perform weighting on a group basis. For example, the weight setting unit 15 can divide the six pieces of information included in the related information 193 into multiple groups and assign different weights to each group.

[0102] The memory unit 19 is a storage device that stores programs for realizing each function of the information processing device 10. The memory unit 19 also stores demand information 191, supply information 192, related information 193, value information 194, and trained models 195.

[0103] (Processing by the information processing device 10) Next, we will explain the processes performed by the information processing device 10, referring to Figure 8. Figure 8 is a flowchart showing the processes performed by the information processing device 10.

[0104] First, the attribute information receiving unit 11 receives attribute information of the individual user (S11). For example, the attribute information receiving unit 11 receives information from the resume entered by the individual user into the individual user terminal 20 as attribute information. The attribute information includes information about the individual user's work performance capabilities. Work performance capabilities may include multiple skills, etc. In addition, the attribute information may also include information other than work performance capabilities, such as the number of times the user has changed jobs or their educational background.

[0105] Next, the value estimation unit 12 inputs attribute information into the trained model 195. Based on the received attribute information of the individual user, the value estimation unit 12 uses the trained model 195 to estimate the value of the work performance capabilities included in the attribute information. The trained model 195 is pre-trained in the learning unit 14 using demand information 191, supply information 192, related information 193, and value information 194 as training data.

[0106] Specifically, the value estimation unit 12 inputs attribute information into the trained model 195 (S12). The trained model 195 takes the attribute information as input and estimates the value of the work performance capabilities included in the attribute information. The value estimation unit 12 receives the estimated value from the trained model 195 (S13). Subsequently, the value output unit 13 outputs estimated value information indicating the estimated value (S14). The value output unit 13 displays the estimated value information on, for example, the output unit of the personal user terminal 20.

[0107] Figure 9 shows an example of display information that shows estimated value information. In the figure, as an example, the display information 20a that is displayed on the display screen (output unit) of the personal user terminal 20 is shown.

[0108] As shown in the figure, the displayed information 20a may include a score indicating the magnitude of the estimated value and annual income. If an individual user possesses multiple skills as part of their work performance capabilities, the displayed information 20a may also include scores and compensation corresponding to each skill. Furthermore, the displayed information 20a may include related information that contributed to the estimation result. In this way, by displaying information that influences the value of work performance capabilities, individual users can concretely grasp the value of their own work performance capabilities.

[0109] Furthermore, the value output unit 13 may output estimated value information to the corporate user terminal 30. For example, the value output unit 13 may display estimated value information indicating the work performance capabilities of individual users who have applied for a job on the output unit of the corporate user terminal 30. The value output unit 13 may also display estimated value information indicating the work performance capabilities of individual users who have viewed the job or who have shown interest in the job.

[0110] Although not shown in the diagram, the learning unit 14 may also retrain the trained model 195 using the estimation results. For example, the weight setting unit 15 automatically changes the weights according to the estimation results. Alternatively, the weight setting unit 15 may accept input from the user and manually change the weights. In this way, the estimation accuracy of the trained model 195 can be improved.

[0111] The configuration of the information processing system 1 and the processing performed by the information processing system 1 have been described above. Note that the configuration of the information processing system 1 described above is merely an example and can be modified as appropriate. For example, if some or all of the components of the information processing device 10 are implemented by multiple information processing devices or circuits, these multiple information processing devices or circuits may be centrally located or distributed. For example, the information processing devices or circuits may be implemented in a form where each is connected via a communication network, such as a client-server system or a cloud computing system. Furthermore, the functions of the information processing device 10 may be provided in SaaS (Software as a Service) format.

[0112] For example, in the example shown in Figure 4, the information processing device 10 is equipped with a learning unit 14 and a weight setting unit 15, and stores the generated trained model 195, but it is not limited to this. A device other than the information processing device 10 may be equipped with the functions of the learning unit 14 and the weight setting unit 15, and the trained model 195 may be stored in a device other than the information processing device 10.

[0113] As described above, in the information processing system 1 of this disclosure, the information processing device 10 estimates the work performance capabilities of individual users using a trained model and outputs the estimation result. The trained model estimates the value of work performance capabilities using demand information and supply information, as well as relevant information that may influence at least one of demand and supply. In this way, the information processing device 10 can obtain an estimated value that takes into account the influence of alternative tools and global circumstances. In this way, the information processing system 1 can appropriately evaluate the work performance capabilities of individual users in accordance with changing trends.

[0114] Furthermore, the information processing system 1 can visualize the value of an individual user's current work performance ability by displaying the estimated value on the individual user's terminal. This allows individual users to appropriately recognize the value of their own work performance ability. In addition, it can increase the individual user's motivation to improve their work performance ability.

[0115] Furthermore, Information Processing System 1 may be used in various scenarios for estimating the value of an individual user's work performance capabilities. For example, Information Processing System 1 may be used when a project leader of a DAO (Decentralized Autonomous Organization) distributes revenue considering the market value of each member. Information Processing System 1 can estimate the value corresponding to each member's work performance capabilities (e.g., knowledge expert, project manager, business designer, analyst, engineer, or researcher).

[0116] (Example hardware configuration) Each functional component of the information processing device 10 may be implemented by hardware (e.g., hardwired electronic circuits) or by a combination of hardware and software (e.g., a combination of electronic circuits and programs that control them). The following describes the case where each functional component of the information processing device 10 is implemented by a combination of hardware and software.

[0117] Figure 10 is a block diagram illustrating the hardware configuration of a computer 900 that implements the information processing device 10. The computer 900 may be a dedicated computer designed to implement the information processing device 10, or it may be a general-purpose computer. The computer 900 may also be a portable computer such as a smartphone or tablet device.

[0118] For example, by installing a predetermined application on the computer 900, each function of the information processing device 10 is realized on the computer 900. The above application consists of a program for realizing the functional components of the information processing device 10.

[0119] Computer 900 includes a bus 902, a processor 904, memory 906, a storage device 908, an input / output interface 910, and a network interface 912. The bus 902 is a data transmission path for the processor 904, memory 906, storage device 908, input / output interface 910, and network interface 912 to send and receive data to and from each other. However, the method of connecting the processor 904 and other components to each other is not limited to bus connection.

[0120] The processor 904 is a variety of processors such as a CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (Field-Programmable Gate Array), or quantum processor (quantum computer control chip). The memory 906 is the main memory, implemented using RAM (Random Access Memory), etc. The storage device 908 is the auxiliary storage, implemented using a hard disk, SSD (Solid State Drive), memory card, or ROM (Read Only Memory), etc.

[0121] The input / output interface 910 is an interface for connecting the computer 900 with input / output devices. For example, input devices such as keyboards and output devices such as display devices are connected to the input / output interface 910.

[0122] The network interface 912 is an interface for connecting computer 900 to a network. This network may be a LAN (Local Area Network) or a WAN (Wide Area Network).

[0123] The storage device 908 stores programs that implement each functional component of the information processing device 10 (programs that implement the aforementioned applications). The processor 904 reads these programs into memory 906 and executes them to implement each functional component of the information processing device 10.

[0124] Each processor executes one or more programs containing a set of instructions for causing the computer to perform the algorithms described with reference to the drawings. These programs, when loaded into the computer, contain a set of instructions (or software code) for causing the computer to perform one or more functions described in the embodiments. The programs may be stored on various types of non-transitory computer-readable medium or tangible storage medium. Examples, but not limited to, include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD), or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray® disc, or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage, or other magnetic storage devices. The programs may also be transmitted over various types of transient computer-readable medium or communication medium. For example, and not an exhaustive, temporary computer-readable or communication media include propagating signals of electrical, optical, acoustic, or other forms.

[0125] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure can be made as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0126] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated with one or more other embodiments, rather than being associated with only one specific embodiment. As those skilled in the art will understand, 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, for example, to create embodiments not explicitly shown or described. Not all features or steps shown in any one drawing are necessarily required to illustrate an exemplary embodiment, and some features or steps may be omitted. The order of steps shown in any of the drawings may be changed as appropriate.

[0127] Some or all of the above embodiments may also be described as follows, but are not limited to the following: (Note 1) An attribute information receiving unit that receives personal attribute information, A value estimation unit estimates the value of the work performance capabilities included in the attribute information by using a trained model that has been trained using the following as training data: demand information regarding the demand for work performance capabilities, supply information regarding the supply of work performance capabilities, related information that may influence at least one of the demand and the supply, and value information indicating the value of the work performance capabilities, based on the individual attribute information received by the attribute information receiving unit. The system includes a value output unit that outputs estimated value information indicating the value estimated by the value estimation unit. Information processing device. (Note 2) The system further includes a weight setting unit that sets a weight for at least one of the demand information, the supply information, and the related information, The trained model is trained using the weights set in the weight setting unit. The information processing device described in Appendix 1. (Note 3) The weight setting unit receives input from the setter and sets the weights. The information processing device described in Appendix 2. (Note 4) The trained model acquires information extracted using natural language processing as related information and performs training using the acquired related information. The information processing device described in Appendix 1 or 2. (Note 5) The trained model learns using future market values ​​estimated based on the demand information, supply information, and related information at multiple different time periods. An information processing device as described in any one of the appendices 1 to 4. (Note 6) The aforementioned related information includes information regarding alternative means of performing the aforementioned tasks, The trained model is trained such that the value decreases as at least one of the quality and quantity of the alternative increases. An information processing device as described in any one of the appendices 1 to 5. (Note 7) The aforementioned trained model is The demand information is obtained based on multiple job postings, and the supply information is obtained based on the attribute information of multiple individuals. The acquired demand information and supply information are used as training data for learning. An information processing device as described in any one of the appendices 1 to 6. (Note 8) The aforementioned related information includes information on trends in the industry to which the job seeker belongs. An information processing device as described in any one of the appendices 1 to 7. (Note 9) The aforementioned related information includes information extracted from the aforementioned employer or publications issued in the aforementioned industry. The information processing device described in Appendix 8. (Note 10) An input layer that accepts input of demand information relating to the demand for work performance capabilities, supply information relating to the supply of said work performance capabilities, and related information that may influence at least one of said demand and said supply, The system includes an output layer that estimates and outputs the value of the business execution capability corresponding to the demand information, the supply information, and the related information, To make a computer function so that it inputs the job performance capabilities included in an individual's attribute information into the input layer and outputs the estimated value from the output layer A pre-trained model. (Note 11) Learning is performed using weights set for at least one of the demand information, supply information, and related information. The trained model described in Appendix 10. (Note 12) An attribute information reception step that receives personal attribute information, A value estimation step is performed using a trained model that has been trained with the following as training data: demand information regarding the demand for work performance capabilities, supply information regarding the supply of the work performance capabilities, related information that may influence at least one of the demand and the supply, and value information indicating the value of the work performance capabilities, based on the individual's attribute information received in the attribute information reception step; The value output step includes outputting estimated value information that shows the value estimated in the value estimation step. Information processing methods. (Note 13) The process further comprises a weight setting step of setting a weight for at least one of the demand information, the supply information, and the related information, The trained model is trained using the weights set in the weight setting step. The information processing method described in Appendix 12. (Note 14) In the weight setting step, input is received from the setter and the weights are set. The information processing method described in Appendix 13. (Note 15) The trained model acquires information extracted using natural language processing as related information and performs training using the acquired related information. The information processing method described in Appendix 12 or 13. (Note 16) The trained model learns using future market values ​​estimated based on the demand information, supply information, and related information at multiple different time periods. The information processing method described in any one of the appendices 12 to 15. (Note 17) The aforementioned related information includes information regarding alternative means of performing the aforementioned tasks, The trained model is trained such that the value decreases as at least one of the quality and quantity of the alternative increases. The information processing method described in any one of the items 12 to 16 of the appendix. (Note 18) The aforementioned trained model is The demand information is obtained based on multiple job postings, and the supply information is obtained based on the attribute information of multiple individuals. The acquired demand information and supply information are used as training data for learning. The information processing method described in any one of the items 12 to 17 of the appendix. (Note 19) An attribute information reception step that receives personal attribute information, A value estimation step is performed using a trained model that has been trained with the following as training data: demand information regarding the demand for work performance capabilities, supply information regarding the supply of the work performance capabilities, related information that may influence at least one of the demand and the supply, and value information indicating the value of the work performance capabilities, based on the individual's attribute information received in the attribute information reception step; A value output step that outputs estimated value information showing the value estimated in the value estimation step, and a computer to execute these steps. program. (Note 20) The computer is further made to perform a weight setting step of setting weights for at least one of the demand information, the supply information, and the related information. The trained model is trained using the weights set in the weight setting step. The program described in Appendix 19.

[0128] Some or all of the elements (e.g., configuration and function) described in Appendices 2 to 9 that are subordinate to Appendice 1 may also be subordinate to Appendices 10, 12, and 19 in the same manner as those described in Appendices 2 to 9. Some or all of the elements described in any appendice may be applied to various hardware, software, recording means, systems, and methods for recording software.

[0129] This application claims priority based on Japanese Patent Application No. 2022-205626, filed on 22 December 2022, and incorporates all of its disclosures herein. [Explanation of symbols]

[0130] 1. Information Processing System 10 Information Processing Devices 11. Attribute Information Reception Department 12 Value Estimation Unit 13 Value Output Unit 14. Learning Department 15. Weight setting section 19 Memory section 20. Personal user terminals 20a Display information 30 Enterprise User Terminals 100 Information Processing Devices 101 Attribute Information Reception Department 102 Value Estimation Unit 103 Value Output Unit 191 Demand information 192 Supply information 193 Related Information 194 Value Information 195 Pre-trained models 900 Computers 902 Bus 904 Processor 906 memory 908 Storage Devices 910 Input / Output Interface 912 Network Interface L1 Input Layer L2 middle layer L3 Output Layer N Network

Claims

1. An attribute information receiving method that accepts personal attribute information, Value estimation means for estimating the value of the work performance ability included in the attribute information, wherein the attribute information of an individual received by the attribute information receiving means is input into a trained model that has been trained using the following as training data: demand information regarding the demand for work performance ability, supply information regarding the supply of the work performance ability, related information that may influence at least one of the demand and the supply, and value information indicating the value of the work performance ability, wherein the related information includes information on tools that substitute for the work performance ability. The system includes a value output means that outputs estimated value information indicating the value estimated by the value estimation means. Information processing device.

2. The system further comprises weight setting means for setting a weight for at least one of the demand information, the supply information, and the related information, The trained model is trained using the weights set by the weight setting means. The information processing apparatus according to claim 1.

3. The weight setting means receives input from the setter and sets the weights. The information processing apparatus according to claim 2.

4. The trained model acquires information extracted using natural language processing as related information and performs training using the acquired related information. The information processing apparatus according to claim 1 or 2.

5. The trained model learns using future market values ​​estimated based on the demand information, supply information, and related information at multiple different time periods. The information processing apparatus according to claim 1 or 2.

6. The aforementioned related information includes information regarding alternative means of performing the aforementioned tasks, The trained model is trained such that the value decreases as at least one of the quality and quantity of the alternative increases. The information processing apparatus according to claim 1 or 2.

7. The aforementioned trained model is The demand information is obtained based on multiple job postings, and the supply information is obtained based on the attribute information of multiple individuals. The acquired demand information and supply information are used as training data for learning. The information processing apparatus according to claim 1 or 2.

8. An input layer that accepts input of demand information relating to the demand for work performance capabilities, supply information relating to the supply of said work performance capabilities, and related information that may influence at least one of said demand and said supply, The system includes an output layer that estimates and outputs the value of the business execution capability corresponding to the demand information, the supply information, and the related information, A trained model for causing a computer to function such that it inputs the ability to perform tasks included in an individual's attribute information into the input layer and outputs an estimated value from the output layer, The aforementioned related information includes information on tools that substitute for the aforementioned ability to perform the tasks, The aforementioned demand information, supply information, related information, and value information indicating the value of the ability to perform the work are pre-trained as training data. A pre-trained model.

9. We accept personal attribute information, The received individual attribute information is input into a trained model that has been trained using demand information regarding the demand for work performance capabilities, supply information regarding the supply of said work performance capabilities, related information that may influence at least one of said demand and said supply, and value information indicating the value of said work performance capabilities as training data, in order to estimate the value of the work performance capabilities included in said attribute information. Output estimated value information showing the estimated value, The aforementioned related information includes information on tools that substitute for the aforementioned ability to perform the tasks, Information processing methods.

10. We accept personal attribute information, The received individual attribute information is input into a trained model that has been trained using demand information regarding the demand for work performance capabilities, supply information regarding the supply of said work performance capabilities, related information that may influence at least one of said demand and said supply, and value information indicating the value of said work performance capabilities as training data, in order to estimate the value of the work performance capabilities included in said attribute information. Output estimated value information showing the estimated value, The aforementioned related information causes the computer to include information about tools that substitute for the ability to perform the aforementioned tasks. program.

Images