Ordering company selection device, ordering company selection method and ordering company selection program

Abstract

To provide an ordering company selection device, an ordering company selection method and an ordering company selection program capable of reducing work of selecting a contractor.SOLUTION: An ordering company selection device 1 includes a reception unit 181 for accepting inputs of multiple pieces of estimation sheet data that are different from one another from respective contractors and a prompt instruction to instruct comparison results of the contractors based on ordering company selection axis information including past contraction information of the respective contractors and one or more selection references, an acquisition unit 182 for inputting the multiple pieces of estimation sheet data and the prompt instruction to a generative AI model to acquire comparison results of the constructors outputted by the generative AI model, and an output control unit 183 for outputting the comparison results.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a contractor selection device, a contractor selection method, and a contractor selection program. [Background technology]

[0002] Conventionally, there is known technology in cost estimation systems that can create accurate estimates consistent with individual differences, even if the user does not accurately remember detailed product knowledge, the unit prices set by the company for customers and suppliers, or the different calculation formulas for each order recipient, and that can reduce the labor required for estimates and speed up the process (see, for example, Patent Document 1).This technology stores the inconsistent product data held by each manufacturer in a unified format to create cost estimation estimates for building and interior construction work. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2000-48071 Summary of the Invention [Problem to be solved by the invention]

[0004] However, when placing an order with a construction contractor, the construction contractor must take into consideration not only the multiple quotations from each of the multiple contractors, but also the past construction content and construction examples of each of the multiple contractors, and select the most appropriate contractor from among the multiple contractors, which requires a great deal of effort.

[0005] The present invention has been made in consideration of the above, and aims to provide a contractor selection device, a contractor selection method, and a contractor selection program that can reduce the selection work of construction contractors. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the object, the contractor selection device of the present invention comprises: a reception unit that receives input of multiple different quotation data from multiple contractors and a prompt instruction that indicates a comparison result of contractors based on contractor selection axis information including past construction information of each of the multiple contractors and one or more selection criteria; an acquisition unit that inputs the multiple quotation data and the prompt instruction into a generation AI model that performs machine learning using past construction case data, the contractor selection axis information, and past quotation data as training data, and generates and outputs the comparison result of the contractors, and acquires the comparison result of the multiple contractors output by the generation AI model; and an output control unit that outputs the comparison result.

[0007] Furthermore, the contractor selection method of the present invention is a contractor selection method executed by a contractor selection device, and includes: a receiving step of receiving input of a plurality of different quotation data from a plurality of contractors and a prompt instruction indicating a comparison result of contractors based on contractor selection axis information including past construction information of each of the plurality of contractors and one or more selection criteria; an acquisition step of inputting the plurality of quotation data and the prompt instruction into a generation AI model that performs machine learning using past construction case data, the contractor selection axis information, and past quotation data as training data, and generates and outputs the comparison result of the contractors, and acquiring the comparison result of the plurality of contractors output by the generation AI model; and an output control step of outputting the comparison result.

[0008] In addition, the contractor selection program of the present invention causes a contractor selection device to execute a receiving step of receiving input of multiple different quotation data from multiple contractors and a prompt instruction that indicates a comparison result of contractors based on contractor selection axis information including past construction information of each of the multiple contractors and one or more selection criteria; an acquisition step of inputting the multiple quotation data and the prompt instruction into a generation AI model that performs machine learning using past construction case data, the contractor selection axis information, and past quotation data as training data, and generates and outputs the comparison result of the contractors, and acquiring the comparison result of the multiple contractors output by the generation AI model; and an output control step of outputting the comparison result. [Effects of the Invention]

[0009] The present invention has the effect of reducing the workload of selecting a construction contractor. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram showing a functional configuration of a contractor selecting device according to the first embodiment of the present invention. [Figure 2] FIG. 2 is a flowchart showing an outline of the processing executed by the contractor selecting device according to the first embodiment of the present invention. [Figure 3] FIG. 3 is a schematic diagram illustrating an outline of the processing executed by the contractor selecting device according to the first embodiment of the present invention. [Figure 4] FIG. 4 is a diagram showing an example of a supplier selection basis table including one or more selection criteria. [Figure 5] FIG. 5 is a block diagram showing a functional configuration of a contractor selecting device according to the second embodiment of the present invention. [Figure 6] FIG. 6 is a flowchart showing an outline of the processing executed by the contractor selecting device according to the second embodiment of the present invention. [Figure 7] FIG. 7 is a schematic diagram illustrating an outline of the processing executed by the contractor selecting device according to the second embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0011] The supplier selection device according to the present disclosure will be described in detail below with reference to the drawings. Note that the present disclosure is not limited to the following embodiments. Furthermore, the drawings referred to in the following description merely show a rough outline of the shape, size, and positional relationship to the extent that the contents of the present disclosure can be understood. In other words, the present disclosure is not limited to only the shape, size, and positional relationship exemplified in each drawing.

[0012] (Embodiment 1) [Functional configuration of the contractor selection device] Figure 1 is a block diagram showing the functional configuration of a contractor selection device according to embodiment 1. The contractor selection device 1 shown in Figure 1 is configured using, for example, a desktop personal computer, a laptop personal computer, or a tablet personal computer. The contractor selection device 1 includes an input unit 11, a reading unit 12, a communication unit 13, a display unit 14, an output unit 15, a recording unit 16, a construction example information database 17 (hereinafter simply referred to as "construction example information DB 17"), and a control unit 18.

[0013] The input unit 11 is configured using input interfaces such as a keyboard, a microphone, a mouse, a touch panel, and a memory card reader. The input unit 11 accepts input of various operations by the user and outputs signals corresponding to the accepted operations to the control unit 18. The input unit 11 also accepts input of voice uttered by the user, converts the accepted voice into voice data, and outputs the voice data to the control unit 18. Note that the input unit 11 may convert the voice into voice data and accept input as text data by converting the voice data of the voice uttered by the user into text, instead of converting the voice into voice data.

[0014] The reading unit 12 is configured using, for example, a memory card reader capable of reading data from a recording medium such as a memory card, or a scanner with an imaging function. The reading unit 12 captures images of a plurality of estimates from a plurality of construction companies to generate a plurality of pieces of estimate data, and outputs this generated estimate data to the control unit 18. Note that, when the estimates from the plurality of construction companies are data, the reading unit 12 reads the estimate data stored in the recording medium from the recording medium and outputs this read estimate data to the control unit 18.

[0015] Under the control of the control unit 18, the communication unit 13 communicates with an external server or the like via a network configured, for example, by the Internet network or a mobile phone network, and outputs various information received from the external server to the control unit 18. Also, under the control of the control unit 18, the communication unit 13 transmits various information input from the control unit 18 to the external server or the like. The communication unit 13 is configured using, for example, a communication module capable of Wi-Fi (registered trademark) or Bluetooth (registered trademark).

[0016] The display unit 14 is configured using a display such as a liquid crystal display or an organic EL display, etc. The display unit 14 displays various information under the control of the control unit 18.

[0017] The output unit 15 is configured using, for example, a speaker, a printer, etc. The output unit 15 outputs various information under the control of the control unit 18. The output unit 15 also outputs printed materials corresponding to the various information under the control of the control unit 18.

[0018] The recording unit 16 is configured using a hard disk drive (HDD), a solid state drive (SSD), a flash memory, a volatile memory, a non-volatile memory, etc. The recording unit 16 has a program recording unit 161 that records various programs executed by the ordering company selection device 1, and a generative artificial intelligence (AI) recording unit 162 that records a generative AI model.

[0019] Here, the generative AI model is a model that newly generates and outputs predetermined information based on predetermined externally input data, such as image data, video data, spreadsheet data (e.g., Excel data (registered trademark) or Word data (registered trademark)), and PDF data, and prompt instructions (text or voice instructions) entered by the user through the input unit 11. For example, the generative AI model is a trained model that performs machine learning using training data that links past construction case data, contractor selection axis information including one or more selection criteria described below, and past estimate data, and generates selection axes not included in the input contractor selection axis information in response to multiple estimate data and prompt instructions (text or voice instructions), and generates and outputs comparison results of the optimal contractor or multiple contractors. Machine learning using training data can use known techniques, including neural networks, etc.

[0020] The construction example information DB17 is configured using an HDD, an SSD, or the like. The construction example information DB17 records construction example information relating to construction examples that have been carried out in the past by each contractor, when an orderer such as a user places orders with each of multiple contractors. Specifically, the construction example information includes the construction period, the order amount, the number of people with required qualifications, whether they exist, the number of personnel, the number of supervisors, whether there has been a man-made accident, whether there has been a schedule, the quality, the capital of the contractor, etc.

[0021] The control unit 18 is realized using a processor having hardware such as an FPGA (Field-Programmable Gate Array), a GPU (Graphics Processing Unit), or a CPU (Central Processing Unit), and a memory that is a temporary storage area used by the processor. The control unit 18 controls each unit that constitutes the ordering company selection device 1. The control unit 18 has a reception unit 181, an acquisition unit 182, an output control unit 183, and an update unit 184.

[0022] The reception unit 181 receives input of multiple different quotation data from multiple construction companies input from the reading unit 12, and a prompt instruction that indicates the comparison results of construction companies based on past construction information of each of the multiple construction companies input by the user via the input unit 11 and contractor selection axis information including one or more selection criteria.

[0023] The acquisition unit 182 inputs multiple different quotation data and prompt instructions received by the reception unit 181 into the generation AI model recorded by the generation AI recording unit 162, and acquires the comparison results for selecting a construction company, which are comparison results obtained by comparing multiple construction companies and are generated and output by the generation AI model.

[0024] The output control unit 183 causes the display unit 14 to display the comparison result acquired by the acquisition unit 182 from the generated AI model.

[0025] The update unit 184 stores in the construction example information DB 17 construction example information in which the construction information ordered by the user input via the input unit 11 was carried out, and updates the construction example information.

[0026] [Processing of the contractor selection device] Next, a description will be given of the processing executed by the contractor selection device 1. Fig. 2 is a flowchart showing an outline of the processing executed by the contractor selection device 1. Fig. 3 is a schematic diagram showing an outline of the processing executed by the contractor selection device 1.

[0027] As shown in Fig. 2, first, the reading unit 12 acquires a plurality of quotations from a plurality of contractors (step S101). Specifically, as shown in Fig. 3, the reading unit 12 generates a plurality of pieces of quotation data by capturing images of a plurality of quotations P1 to P3 from a plurality of contractors, each in a different format, and outputs the plurality of pieces of quotation data to the control unit 18. Note that the ordering contractor selection device 1 can omit the processing of step S101 if the quotations are not printed materials such as paper.

[0028] Next, the reception unit 181 receives the multiple pieces of mutually different estimate data and a prompt instruction input by the user via the input unit 11 (step S102). For example, if the multiple estimates for the multiple contractors are on paper, the reception unit 181 receives the multiple pieces of mutually different estimate data input from the reading unit 12 and a prompt instruction input by the user via the input unit 11. Furthermore, if the multiple pieces of mutually different estimate data have been transmitted from an external PC or the like, the reception unit 181 receives the multiple pieces of mutually different estimate data for the multiple contractors input via the communication unit 13 or the reading unit 12 and a prompt instruction input by the user via the input unit 11.

[0029] The acquisition unit 182 then inputs the multiple estimate data and prompt instructions received by the reception unit 181 into the generation AI model recorded by the generation AI recording unit 162, and acquires a comparison result for selecting a contractor, which is a comparison result obtained by comparing each of the multiple contractors (step S103). Specifically, as shown in FIG. 3, the acquisition unit 182 inputs the multiple estimate data for each of the multiple estimates P1 to P3 and a prompt instruction such as "Please rank the contractors based on the comparison items and past construction results" into the generation AI model, and acquires a comparison result T1 for selecting a contractor (hereinafter simply referred to as "ordering contractor") to be commissioned to perform construction (work) from among the multiple contractors. In this case, the generation AI model generates a comparison result T1 based on newly constructed selection criteria for selecting a contractor based on the multiple estimate data and prompt instructions, using a trained model machine-learned using training data that links the ordering contractor selection base table T10, which includes one or more selection criteria shown in FIG. 4, construction case information in the construction case information DB17, and past estimate data. In the case shown in Figure 4, the generative AI model establishes a new score for each item for each contractor, and generates and outputs a comparison result T1 that includes a total score obtained by adding up these scores.

[0030] Next, the output control unit 183 causes the display unit 14 to display the comparison result acquired by the acquisition unit 182 from the generative AI model (step S104). Specifically, as shown in FIG. 3, the output control unit 183 causes the display unit 14 to display the comparison result T1. This allows the user to intuitively select a contractor without much work, even for multiple quotations in different formats, based on the score criteria for each item newly constructed by the generative AI model. Furthermore, because the comparison result T1 includes scores for each item in addition to the total score, the user can easily select a contractor with a high score according to the item the user values ​​most.

[0031] Thereafter, if the receiving unit 181 receives a new prompt instruction via the input unit 11 (step S105: Yes), the acquiring unit 182 inputs the new prompt instruction received by the receiving unit 181 into the generation AI model recorded by the generation AI recording unit 162, and acquires a new comparison result in accordance with the new prompt instruction (step S106). After step S106, the supplier selection device 1 returns to step S104, and displays a new comparison result in accordance with the new prompt instruction on the display unit 14. In this way, if the user is not satisfied with the comparison result of the generation AI model, the supplier selection device 1 inputs a new prompt instruction to the generation AI model each time the user inputs a new prompt instruction via the input unit 11, acquires a new comparison result in accordance with the new prompt instruction, and displays the new comparison result on the display unit 14 or outputs the comparison result to the output unit 15.

[0032] In step S105, if the receiving unit 181 has not received a new prompt instruction via the input unit 11 (step S105: No), the update unit 184 stores in the construction example information DB 17 the construction example information in which the construction information ordered by the user input via the input unit 11 was performed, and updates it (step S107). Specifically, the update unit 184 stores in the construction example information DB 17 the construction example information including the contractor, the total score output by the generation AI model, the score for each item, the construction scale, the amount, etc., and updates it.

[0033] According to the embodiment 1 described above, the acquisition unit 182 inputs the multiple quotation data and prompt instructions received by the reception unit 181 into the generation AI model recorded in the generation AI recording unit 162, and acquires the comparison results for selecting a construction company, which are comparison results obtained by comparing multiple construction companies using criteria based on scores for each item newly constructed by the generation AI model, and the output control unit 183 displays the comparison results acquired from the generation AI model by the acquisition unit 182 on the display unit 14, thereby reducing the work of selecting a construction company.

[0034] (Embodiment 2) Next, a second embodiment will be described. In the first embodiment described above, multiple pieces of quotation data having different formats and prompt instructions are input to a generation AI model, and the generation AI model generates and outputs a comparison result for selecting a contractor from multiple contractors based on the multiple quotations having different formats. In the second embodiment, however, multiple pieces of quotation data having different formats are converted into the same format by a first generation AI model, and this multiple pieces of quotation data in the same format are input to a second generation AI model, which outputs a comparison result. Therefore, the contractor selection device according to the second embodiment has a different configuration from the contractor selection device 1 according to the first embodiment described above, and also executes different processes. In the following, the same components as those of the contractor selection device 1 according to the second embodiment are assigned the same reference numerals, and detailed description thereof will be omitted.

[0035] [Configuration of the contractor selection device] Fig. 5 is a block diagram showing the functional configuration of a contractor selection device according to embodiment 2. The contractor selection device 1A shown in Fig. 5 includes a recording unit 16A and a control unit 18A instead of the recording unit 16 and the control unit 18 of the contractor selection device 1 according to embodiment 1 described above.

[0036] The recording unit 16A further includes a first generated AI recording unit 163 and a second generated AI recording unit 164 in addition to the program recording unit 161 of the recording unit 16A provided in the contractor selection device 1 relating to the above-mentioned embodiment 1.

[0037] The first generative AI recording unit 163 records a first generative AI model. Here, the first generative AI model is a trained model that performs machine learning using multiple pieces of estimate data in different formats and multiple pieces of estimate data in the same format as training data, and generates and outputs estimate data in the same format. In other words, the first generative AI model performs machine learning using training data that links multiple pieces of estimate data in different formats with multiple pieces of estimate data in the same format, and outputs newly generated estimate data in the same format in response to this and prompt instructions (text or voice instructions). This generative AI model may cooperate with an external generative AI model such as Stable Diffusion, Mid Journey, DALL E3, or SeaArt to generate estimate data in the same format. In the second embodiment, the first generative AI model functions as a generative AI model different from the generative AI model in the first embodiment.

[0038] The second generation AI recording unit 164 records the same teacher data and a second generation AI model that has undergone machine learning as the generation AI recording unit 162 according to the above-described first embodiment. This second generation AI model is a trained model that generates a selection axis that is not included in the input contractor selection axis information in response to multiple pieces of quotation data in the same format and prompt instructions (instructions by text or voice), and generates and outputs a comparison result of the optimal contractor or multiple contractors.

[0039] The control unit 18A further includes a format acquisition unit 185 in addition to the functional configuration of the control unit 18 of the ordering company selecting device 1 according to the first embodiment described above.

[0040] The format acquisition unit 185 inputs a format prompt instruction that indicates multiple pieces of quotation data and the type of format to the first generation AI model recorded by the first generation AI recording unit 163, and acquires multiple pieces of quotation data generated in the same format output by the first generation AI model.

[0041] [Processing of the contractor selection device] Next, the processing executed by the supplier selection device 1A will be described. Fig. 6 is a flowchart showing an outline of the processing executed by the supplier selection device 1A. Fig. 7 is a schematic diagram showing an outline of the processing executed by the supplier selection device 1A.

[0042] As shown in Fig. 6, first, the reading unit 12 acquires a plurality of quotations from a plurality of contractors (step S201). Specifically, as shown in Fig. 7, the reading unit 12 captures images of a plurality of quotations P1 to P3 from a plurality of contractors, each quotations having a different format, to generate a plurality of pieces of quotation data, and outputs the plurality of quotation data to the control unit 18A.

[0043] Next, the accepting unit 181 accepts the plurality of pieces of quotation data input from the reading unit 12 and a prompt instruction instructing the format of the quotation data input by the user via the input unit 11 (step S202).

[0044] Thereafter, the format acquisition unit 185 inputs the multiple estimate data received by the reception unit 181 and a prompt instruction specifying the format of the estimate data to the first generation AI model recorded by the first generation AI recording unit 163, and acquires multiple estimate data converted into the same format (step S203). Specifically, as shown in FIG. 7, for example, the format acquisition unit 185 inputs multiple estimate data for each of multiple quotations P1 to P3 and a prompt instruction saying "Please output the input estimates in the same format" to the first generation AI model, and acquires multiple estimate data P11 to P13 in the same format. Note that the format of the newly generated same format includes the same items such as date, item name, quantity, unit price, and amount, and also includes additional items not present in estimate P1, such as item name, quantity, and unit price.

[0045] Next, the output control unit 183 displays the multiple pieces of quotation data P11 to P13 in the same format acquired from the first generative model by the format acquisition unit 185 on the display unit 14 (step S204). This allows the user to check the output results of the first generative AI model, that is, whether the data for each item is correct and valid.

[0046] Thereafter, when the receiving unit 181 receives a new prompt instruction for the first generative AI model via the input unit 11 (step S205: Yes), the acquiring unit 182 inputs the new prompt instruction received by the receiving unit 181 to the first generative AI model recorded by the first generative AI recording unit 163, and acquires a plurality of pieces of quotation data converted into a new, identical format in accordance with the new prompt instruction (step S206). After step S206, the supplier selection device 1A returns to step S204, and displays the plurality of pieces of quotation data converted into a new, identical format in accordance with the new prompt instruction on the display unit 14. In this way, when the user is not satisfied with the content of the plurality of pieces of quotation data converted into a new, identical format of the first generative AI model, the supplier selection device 1A inputs a new prompt instruction to the first generative AI model each time the user inputs a new prompt instruction for the first generative AI model via the input unit 11, acquires a plurality of pieces of quotation data converted into a new, identical format in accordance with the new prompt instruction, and displays the acquired data on the display unit 14 or outputs a comparison result to the output unit 15.

[0047] In step S205, if the receiving unit 181 has not received a new prompt instruction for the first generation AI model via the input unit 11 (step S205: No), the ordering company selection device 1A proceeds to step S207.

[0048] Next, the accepting unit 181 accepts a plurality of pieces of quotation data in the same format and a prompt instruction input by the user via the input unit 11 (step S207).

[0049] Next, the acquisition unit 182 inputs the multiple estimate data in the same format received by the reception unit 181 and the prompt instruction into the second generation AI model recorded by the second generation AI recording unit 164, and acquires the comparison results for selecting a contractor from the multiple contractors, which are comparison results obtained by comparing each of the multiple contractors (step S208). Specifically, as shown in FIG. 7, the acquisition unit 182 inputs the multiple estimate data for each of the multiple estimates P1 to P3 and the prompt instruction, "Please rank the contractors based on the comparison items and past construction results," into the generation AI model, and acquires the comparison result T1 for selecting a contractor. In this case, as shown in FIG. 4, the generation AI model references the contractor selection base table T10 and the construction case information DB 17, and generates and acquires the comparison result T1 for selecting a contractor based on the multiple estimate data and the prompt instruction. In the case shown in FIG. 4, the generation AI model generates and outputs the comparison result T1 for each contractor, including a total score obtained by adding up the scores for each item.

[0050] Thereafter, the output control unit 183 causes the display unit 14 to display the comparison result acquired by the acquisition unit 182 from the second generative AI model (step S209). Specifically, as shown in FIG. 7, the output control unit 183 causes the display unit 14 to display the comparison result T1. This allows the user to intuitively select a contractor without much work, even for multiple quotations in different formats, based on the score criteria for each item newly constructed by the second generative AI model. Furthermore, because the score for each item is included in addition to the total score of the comparison result T1, the user can easily select a contractor with a high score according to the item that the user values ​​most.

[0051] Thereafter, when the receiving unit 181 receives a new prompt instruction for the second generation model via the input unit 11 (step S210: Yes), the acquiring unit 182 inputs the new prompt instruction for the second generation model received by the receiving unit 181 to the second generation AI model recorded by the second generation AI recording unit 164, and acquires a new comparison result in accordance with the new prompt instruction (step S211). After step S211, the ordering contractor selection device 1A returns to step S209 and displays a new comparison result in accordance with the new prompt instruction on the display unit 14. In this way, when the user is not satisfied with the comparison result of the second generation AI model, the ordering contractor selection device 1A inputs a new prompt instruction to the second generation AI model each time the user inputs a new prompt instruction via the input unit 11, acquires a new comparison result in accordance with the new prompt instruction, and displays it on the display unit 14 or outputs the comparison result to the output unit 15.

[0052] In step S210, if the receiving unit 181 has not received a new prompt instruction for the second generation model via the input unit 11 (step S210: No), the ordering contractor selection device 1A proceeds to step S212.

[0053] Step S212 corresponds to step S107 in Fig. 2, and therefore detailed description thereof will be omitted. After step S212, the supplier selection device 1A ends this process.

[0054] According to the above-described embodiment 2, the output control unit 183 displays multiple quotation data in the same format acquired from the first generative model by the format acquisition unit 185 on the display unit 14, so that the user can confirm whether the output result of the first generative AI model is appropriate.

[0055] Furthermore, according to the second embodiment, similar to the first embodiment described above, the output control unit 183 displays the comparison results acquired from the generated AI model by the acquisition unit 182 on the display unit 14, thereby reducing the work of selecting a construction contractor.

[0056] (Other embodiments) In the contractor selection device according to the first and second embodiments described above, the generation AI model is stored in the recording unit, but this is not limited to this. A prompt instruction indicating the comparison results for selecting a contractor, which are comparison results obtained by comparing multiple pieces of quotation data in different formats or multiple pieces of quotation data in the same format with multiple construction contractors, may be sent to an external generation AI model via a network, and the comparison results may be received from the external generation AI model and displayed.

[0057] Furthermore, although the contractor selection device according to the first and second embodiments includes a construction example information DB, the present invention is not limited to this and may be configured to be connected to the construction example information DB via a network.

[0058] In addition, in the second embodiment, the contractor selection device stores the first and second generative AI models in the storage unit, but the present invention is not limited to this. The contractor selection device may transmit multiple pieces of quotation data in different formats and prompt instructions to an external first generative AI model via a network, and obtain multiple pieces of quotation data in the same format. In this case, the contractor selection device may further transmit multiple pieces of quotation data in the same format to the second generative AI model and prompt instructions, and receive a comparison result for selecting a contractor, which is a comparison result obtained by comparing each of the multiple contractors.

[0059] In addition, in both of the above-described first and second embodiments, an estimate is determined and a contractor is selected based on a single output result of the generative AI model, but a configuration may also be adopted in which a person can confirm the output result of the generative AI model once output and input a new prompt instruction again, causing the generative AI model to output a different output result again.In this case, the above-described construction example information DB17 may be updated with information related to the last output result, or the information may be updated along with the history each time it is output.

[0060] Furthermore, in the contractor selection device according to the first and second embodiments described above, various inventions can be formed by appropriately combining multiple components. For example, some components may be deleted from all of the components described in the contractor selection device according to the embodiments of the present disclosure described above. Furthermore, the components described in the contractor selection device according to the embodiments of the present disclosure described above may be appropriately combined.

[0061] Furthermore, in the contractor selection device according to the first and second embodiments, the "unit" described above can be read as "means" or "circuit," etc. For example, the control unit can be read as control means or control circuit.

[0062] In addition, the programs to be executed by the contractor selection device according to embodiments 1 and 2 are provided as file data in an installable or executable format recorded on a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, a DVD (Digital Versatile Disk), a USB medium, or a flash memory.

[0063] Furthermore, the programs executed by the ordering company selection devices according to the first and second embodiments may be configured to be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network.

[0064] In the explanation of the flowcharts in this specification, the order of processing between steps is clearly indicated using expressions such as "first," "then," and "continue," but the order of processing required to implement the present invention is not uniquely determined by these expressions. In other words, the order of processing in the flowcharts described in this specification can be changed within a consistent range.

[0065] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that have undergone various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the disclosure of the present invention. [Explanation of symbols]

[0066] 1,1A Contractor selection device 11 Input section 12 Reading unit 13 Communications Department 14 Display section 15 Output section 16,16A Recording section 17 Construction case information database 18,18A Control unit 161 Program Recording Section 162 Generation AI Recording Unit 163 First Generation AI Recording Unit 164 Second Generation AI Recording Unit 181 Reception Department 182 Acquisition Department 183 Output control section 184 Update Department 185 Format Acquisition Section

Claims

1. A reception unit that receives input of a plurality of different estimate data from each of a plurality of contractors, and a prompt instruction that indicates a comparison result of contractors based on past construction information of each of the plurality of contractors and contractor selection axis information including one or more selection criteria; An acquisition unit that performs machine learning using past construction case data, the contractor selection axis information, and past quotation data as training data, inputs the multiple quotation data and the prompt instructions into a generation AI model that generates and outputs a comparison result of the contractors, and acquires the comparison result of the multiple contractors output by the generation AI model; an output control unit that outputs the comparison result; Equipped with Contractor selection device.

2. 2. The contractor selection device according to claim 1, The system further comprises a format acquisition unit that performs machine learning using multiple pieces of quotation data in different formats and multiple pieces of quotation data in the same format as training data, inputs a format prompt instruction that indicates the multiple pieces of quotation data and the type of format to a generation AI model different from the generation AI model that generates and outputs quotation data in the same format, and acquires the multiple pieces of quotation data generated in the same format output by the generation AI model different from the generation AI model, The acquisition unit The plurality of quotation data generated in the same format are input into the generation AI model. Contractor selection device.

3. 3. The contractor selection device according to claim 2, The output control unit Before the acquisition unit inputs the plurality of quotation data generated in the same format into the generation AI model, an output unit outputs the plurality of quotation data generated in the same format so that the plurality of quotation data can be confirmed. Contractor selection device.

4. The contractor selection device according to claim 3, The reception unit a new prompt instruction can be received based on the plurality of quotation data generated in the same format and output by the output unit; The acquisition unit Each time the reception unit receives a new prompt instruction, the new prompt instruction is input into the generation AI model to obtain a new comparison result of the plurality of construction companies; The output control unit outputting a new comparison result of the plurality of construction companies by the output unit; Contractor selection device.

5. 5. The contractor selection device according to claim 4, A construction case information database that records past construction case data; an updating unit that updates the construction example information of the contractor who has been ordered according to the comparison result in the construction example information database; Further provided with Contractor selection device.

6. 6. The contractor selection device according to claim 5, The generative AI model is outputting the results of the comparison, which are sequentially assigned scores for selecting an ordering company to each of the plurality of construction companies; Contractor selection device.

7. 7. The contractor selection device according to claim 6, The generative AI model is outputting, as the comparison result, a score assigned to each of the plurality of construction companies for each selection criterion for selecting an ordering company; Contractor selection device.

8. A contractor selection method executed by a contractor selection device, A receiving step of receiving input of a plurality of different estimate data from each of a plurality of contractors, and a prompt instruction indicating a comparison result of the contractors based on past construction information of each of the plurality of contractors and contractor selection axis information including one or more selection criteria; An acquisition step of inputting the multiple quotation data and the prompt instructions into a generation AI model that performs machine learning using past construction case data, the contractor selection axis information, and past quotation data as training data, generates and outputs a comparison result of the contractors, and acquires the comparison result of the multiple contractors output by the generation AI model; an output control step of outputting the comparison result; Including, How to select a contractor.

9. For the supplier selection device, A receiving step of receiving input of a plurality of different estimate data from each of a plurality of contractors, and a prompt instruction indicating a comparison result of the contractors based on past construction information of each of the plurality of contractors and contractor selection axis information including one or more selection criteria; An acquisition step of inputting the multiple quotation data and the prompt instructions into a generation AI model that performs machine learning using past construction case data, the contractor selection axis information, and past quotation data as training data, generates and outputs a comparison result of the contractors, and acquires the comparison result of the multiple contractors output by the generation AI model; an output control step of outputting the comparison result; Execute Contractor selection program.

Images