Information processing system, information processing program, and information processing method

Abstract

To provide an information processing system capable of supporting creation of a highly satisfactory itinerary to be presented to a customer, even when a sales representative responsible for product planning at a travel agency lacks sufficient experience.SOLUTION: The information processing system includes: means for acquiring travel conditions input by a user; means for generating, using a model trained by machine learning with itineraries implemented in the past and traveler satisfaction levels for the itineraries as training data, an itinerary that satisfies the travel conditions input by the user and is estimated to have relatively high traveler satisfaction; and means for outputting the generated itinerary.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] The products that travel agencies offer to their customers (travelers) can be broadly classified into the following three categories. 1) Arranged travel (products in which the travel agency arranges the items decided by the customer (transportation, accommodation, etc.)) 2) Custom-made package tours (products in which a travel agency creates a travel plan based on a customer's request, such as company trips and school trips) 3) Package tours (products in which a travel agency creates a travel plan in advance and recruits participants. Package tours)

[0003] Regarding custom-order package tours, Patent Document 1 proposes a proposal device that, once a reservation for a travel plan is made, stores and learns the questions asked to propose the travel plan and the answers given by the user in association with the agreed-upon travel plan, and if a similar question and answer session occurs next time or later, can propose a travel plan relatively quickly without having to repeat the question and answer session until the travel plan is made. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2021-39498 Summary of the Invention [Problem to be solved by the invention]

[0005] The current situation for travel agencies regarding custom-order package tours is as follows. In other words, as the number of stores continues to shrink, the very nature of traveling through a travel agency is being called into question. Furthermore, because they have mainly dealt with package tours up until now, they have been unable to respond to diversifying customer demands and have not been able to differentiate themselves from other companies. The reasons for this are thought to be a lack of experience among sales representatives in charge of product planning. Also, it is thought that past travel plans that had a high level of satisfaction among travelers are not being utilized.

[0006] The present invention has been made in consideration of the above points, and an object of the present invention is to provide an information processing system, an information processing program, and an information processing method that can support the creation of highly satisfying itineraries to present to customers, even when the sales representatives in charge of product planning at travel agencies lack experience. [Means for solving the problem]

[0007] The information processing system according to the present invention comprises: A means for acquiring travel conditions input by a user; A means for generating an itinerary that satisfies the travel conditions input by the user and is estimated to have a relatively high level of traveler satisfaction, using a machine-learned model that uses past itineraries and traveler satisfaction levels for those itineraries as training data; means for outputting the generated itinerary; Equipped with. [Effects of the Invention]

[0008] According to the present invention, even if a travel agency has sales staff in charge of product planning who lack experience, it is possible to assist them in creating highly satisfying itineraries to present to customers. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing a schematic configuration of an information processing system according to an embodiment. [Figure 2] FIG. 2 is a flowchart showing an example of the operation of the information processing system according to an embodiment. [Figure 3] FIG. 3 is a diagram for explaining an example of a specific operation in the itinerary generating unit. [Figure 4] FIG. 4 is a diagram illustrating an example of a screen displayed by the information processing system according to an embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a screen displayed by the information processing system according to an embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a screen displayed by the information processing system according to an embodiment. [Figure 7] FIG. 7 is a diagram showing an example of a screen displayed by the information processing system according to an embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a screen displayed by the information processing system according to an embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of a screen displayed by the information processing system according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In each drawing, components having equivalent functions are designated by the same reference numerals, and detailed description of the components having the same reference numerals will not be repeated.

[0011] (Configuration of information processing system) 1 is a diagram showing a schematic configuration of an information processing system 1 according to an embodiment. In the diagram, functional units that perform each function can be said to be means that perform each function.

[0012] As shown in Fig. 1, the information processing system 1 includes a terminal device 2 and a server 3. The terminal device 2 and the server 3 are connected to each other so that they can communicate with each other via a network 4 such as the Internet. The network 4 may be either a wired line or a wireless line, and the type and form of the line are not important. At least a portion of the terminal device 2 and the server 3 are realized by a computer.

[0013] First, we will explain the terminal device 2. The terminal device 2 is used by a user (for example, a sales representative in charge of product planning at a travel agency), and is, for example, an electronic device such as a mobile terminal such as a smartphone or a tablet terminal, a notebook computer, or a desktop computer.

[0014] 1, the terminal device 2 has a terminal communication unit 21, a terminal control unit 22, a terminal storage unit 23, a terminal input unit 24, and a terminal display unit 25. The units 21 to 25 are connected to each other so as to be able to communicate with each other.

[0015] The terminal communication unit 21 is a communication interface between the terminal device 2 and the network 4. The terminal communication unit 21 transmits and receives information between the terminal device 2 and the server 3 via the network 4.

[0016] The terminal control unit 22 is a control means that performs various processes of the terminal device 2. The terminal control unit 22 may be realized by a processor in the terminal device 2 executing a predetermined program, or may be implemented in hardware.

[0017] The terminal storage unit 23 is a data storage such as an internal memory or an external memory (such as an SD memory card). The terminal storage unit 23 stores various data handled by the terminal control unit 22. Note that the terminal storage unit 23 does not necessarily have to be provided within the terminal device 2, and part or all of the terminal storage unit 23 may be provided within another device (for example, on the cloud) that is communicatively connected to the terminal device 2 via the network 4.

[0018] The terminal input unit 24 is an interface for the user to input information to the terminal device 2, and is, for example, a touch panel or microphone in a mobile terminal, or a touch pad, keyboard, or mouse in a notebook computer.

[0019] The terminal display unit 25 is an interface that outputs various information to the user from the terminal device 2, and is, for example, a video display means such as a liquid crystal display. Specifically, for example, the terminal display unit 25 may display a GUI (Graphical User Interface) for receiving operations from the user.

[0020] Next, we will explain the server 3. As shown in Fig. 1, the server 3 has a server communication unit 31, a server control unit 32, and a server storage unit 33. The units 31 to 33 are connected to each other so that they can communicate with each other.

[0021] Of these, the server communication unit 31 is a communication interface between the server 3 and the network 4. The server communication unit 31 transmits and receives information between the server 3 and the terminal device 2 via the network 4.

[0022] The server storage unit 33 is, for example, a fixed data storage such as a hard disk. The server storage unit 33 stores various data handled by the server control unit 32. For example, the server storage unit 33 includes a route network information database 33a including transportation network information and a map information database 33b including map information.

[0023] Transportation network information is information that defines transportation networks such as railroads and buses, as well as road networks. Transportation network information includes transportation route information, timetable information, fare information, etc. Road network information is expressed by combining data on nodes, which are nodes on the road network representation, such as intersections, and data on links, which are road sections between the nodes.

[0024] The map information includes map data such as national and regional road maps, and map object information associated with the map data. The map object information includes shape information about the shapes of facilities displayed on the map, note information about notes displayed on the map, symbol information about symbols displayed on the map, etc. The map information may also include route map information about public transportation route maps.

[0025] The above traffic network information and map information may be updated at predetermined times.

[0026] In addition, the server memory unit 33 does not necessarily have to be located within the server 3, and part or all of the server memory unit 33 may be located within another device that is communicatively connected to the server 3 via the network 4.

[0027] The server control unit 32 has a travel condition acquisition unit 32a, an itinerary generation unit 32b, an itinerary output unit 32c, an area display unit 32d, an itinerary editing unit 32e, and a schedule generation unit 32f. Each of these units 32a to 32f may be realized by a processor in the server 3 executing a predetermined program, or may be implemented in hardware.

[0028] The travel condition acquisition unit 32a acquires travel conditions entered by the user. For example, when the user operates the terminal input unit 24 to interactively input travel conditions as a character string in a natural language into the dialogue area 51 (see FIG. 4) in the display area 50 displayed on the terminal display unit 25, the input character string is transmitted from the terminal device 2 to the server 3, and the travel condition acquisition unit 32a may identify and acquire the travel conditions by performing natural language processing on the received character string. Here, the travel conditions include one or more pieces of information among candidate destinations, itinerary (number of nights and days or a day trip), travel time, departure point, and number of people. The travel conditions may further include one or more of accommodations, facilities at the accommodations (e.g., Japanese-style banquet halls), and activities to be performed during the trip (e.g., fishing, diving, hiking, soba noodle making, shopping, etc.).

[0029] The travel condition acquisition unit 32a may further include traveler attributes entered by the user. Here, the traveler attributes may be information about age (generation) and / or gender. In the case of a company trip, the traveler attributes may also be information about occupation, job type, and / or group size. In the case of a school trip, the traveler attributes may also be information about the size, department, and school atmosphere of the school. In addition, the traveler attributes may also be information about other groups (clubs, etc.). In addition, the traveler attributes may also be information about the travel habits of customers (for example, patterns of selection from multiple plans, which plans they tend to choose, etc.).

[0030] The itinerary generator 32b uses a trained model that has been machine-learned using previously implemented itineraries (also called travel plans) and traveler satisfaction levels for those itineraries as training data to generate an itinerary that meets the travel conditions entered by the user and is estimated to have a relatively high level of traveler satisfaction. Here, the machine learning method is not particularly limited, and may be, for example, one or a combination of two or more of neural networks (including deep learning), support vector machines, Bayesian networks, clustering, decision trees, and random forests (ensemble learning).

[0031] The itinerary generator 32b may use a trained model that has been machine-learned using previously implemented itineraries and traveler satisfaction levels for those itineraries as training data to generate multiple itineraries that satisfy the travel conditions input by the user and are estimated to have relatively high traveler satisfaction levels. The multiple itineraries that are generated may include an itinerary that satisfies at least one item of the travel conditions input by the user but does not satisfy one or more other items (for example, an alternative plan that does not include the candidate destinations input by the user).

[0032] As a modified example, the itinerary generation unit 32b may use a trained model that has been machine-learned using previously implemented itineraries and the satisfaction levels of travelers in those itineraries and the attributes of those travelers as training data to generate an itinerary that satisfies the travel conditions input by the user and that is estimated to have a relatively high level of satisfaction for the attributes of the travelers input by the user. The itinerary generation unit 32b may generate multiple itineraries that are estimated to have a relatively high level of satisfaction for the attributes of the travelers input by the user.

[0033] As another variation, the itinerary generation unit 32b may use a trained model that has been machine-learned using itineraries created by travel agencies in the past, the sales record for those itineraries, and the satisfaction level of travelers for those itineraries as training data to generate an itinerary that meets the travel conditions entered by the user and that is estimated to have a relatively high level of traveler satisfaction and a relatively high rate of sales. The itinerary generation unit 32b may generate multiple itineraries that are estimated to have a relatively high level of traveler satisfaction and a relatively high rate of sales.

[0034] As yet another variant, the itinerary generation unit 32b may use a trained model that has been machine-learned using itineraries created by travel agencies in the past, the sales record for those itineraries, and the satisfaction levels and attributes of travelers in those itineraries as training data to generate an itinerary that meets the travel conditions input by the user and that is estimated to have a relatively high satisfaction level and a high success rate for the attributes of travelers input by the user. The itinerary generation unit 32b may generate multiple itineraries that are estimated to have a relatively high satisfaction level and a high success rate for the attributes of travelers input by the user.

[0035] The itinerary that constitutes the training data may be an itinerary that was previously taken, or may be an itinerary created by a travel agency (or the revised (edited) itinerary if the customer has made any modifications (edits) along the way). Furthermore, the itinerary that constitutes the training data may further include, in addition to information on locations (spots) and means of transportation, information on events that take place during the trip (e.g., karaoke, games, etc. in the car while traveling) and / or items provided during the trip (e.g., meals, snacks, drinks, etc.). Furthermore, the itinerary that constitutes the training data may be an itinerary created between the travel agency and the operator when a quote is requested.

[0036] The training data may further include analysis and evaluation data of the itinerary by the travel agency (for example, whether emphasis is placed on accommodation or tourist attractions and activities, budget percentage, trip theme, etc.).

[0037] The satisfaction level that constitutes the training data may be (1) a value corresponding to the degree to which the customer has modified the itinerary originally created by the travel agency, or (2) satisfaction level (such as questionnaire data) obtained from travelers when the itinerary created by the travel agency is contracted and the trip is carried out. Furthermore, the satisfaction level that constitutes the training data may be satisfaction level for the entire trip, or satisfaction level for each trip. Furthermore, satisfaction levels evaluated by traveler attributes may also be used as training data.

[0038] The contract results constituting the training data may be information indicating that a contract has been concluded, or may be information indicating that a contract has not been concluded.

[0039] The attributes of travelers that make up the training data may be information by age (generation) and / or gender, or in the case of company trips, by occupation, job type, and / or group size, or in the case of school trips, by the size, department, and school atmosphere of the school, or by other groups (clubs, etc.), or by customer travel habits (for example, patterns of choosing between multiple plans, which plans they tend to choose, etc.).

[0040] An example of a specific operation (processing) performed by the itinerary generation unit 32b will be described with reference to FIG. 3. In the example shown in FIG. 3, the itinerary generation unit 32b first formats the travel conditions input by the user (travel conditions acquired by the travel condition acquisition unit 32a) into a prompt to be input to the conversational AI, and then inputs the formatted prompt to the conversational AI. Here, the conversational AI is a generation AI built based on a large-scale language model. For example, ChatGPT by OpenAI or Gemini by Google may be used as the conversational AI. Specifically, for example, as shown in FIG. 3, if the candidate location for the travel conditions input by the user is "Kanazawa," the itinerary generation unit 32b formats the travel conditions into a prompt such as "Please pick three recommended tourist spots in Kanazawa and tell me the names of the spots," and then inputs the formatted prompt to the conversational AI. Then, the itinerary generation unit 32b acquires the output result output from the conversational AI (in the example shown in FIG. 3, the names of the three tourist spots).

[0041] Next, the itinerary generation unit 32b verifies the validity of the output result of the interactive AI by referring to the map information database 33b. Specifically, for example, if "Kanazawa 21st Century Science Museum" is not found in the map information database 33b among the output results of the interactive AI, but instead a similar "Kanazawa 21st Century Museum of Contemporary Art" is found, the itinerary generation unit 32b may replace "Kanazawa 21st Century Science Museum" among the output results of the interactive AI with "Kanazawa 21st Century Museum of Contemporary Art." If no spot name similar to "Kanazawa 21st Century Science Museum" is found, the itinerary generation unit 32b may delete "Kanazawa 21st Century Science Museum" from the output results of the interactive AI.

[0042] The itinerary generating unit 32b may refer to the map information database 33b to acquire the names of additional spots (for example, lunch spots) (other than the output results of the interactive AI).

[0043] Next, the itinerary generation unit 32b obtains multiple circular routes that visit the three tourist spots output by the interactive AI and the additional spots obtained by referring to the map information database 33b through route search, by referring to the route network information database 33a and the map information database 33b.The itinerary generation unit 32b then combines this information (spots and circular routes) to create multiple itinerary (travel plan) candidates that satisfy the travel conditions entered by the user.

[0044] The itinerary generation unit 32b may create, as one of multiple itinerary candidates, an itinerary that satisfies at least one item of the travel conditions input by the user (e.g., schedule, travel time, departure point, number of people) but does not satisfy one or more other items (e.g., candidate locations) (e.g., an alternative plan that does not include the candidate locations input by the user).

[0045] Next, for each itinerary candidate, the itinerary generation unit 32b uses a trained model that has been machine-learned using itineraries created by travel agencies in the past, as well as the sales record and traveler satisfaction for those itineraries, as training data, to estimate traveler satisfaction and sales rate using the itinerary candidate as input.

[0046] Then, the itinerary generation unit 32b identifies (generates) "itineraries estimated to have relatively high traveler satisfaction and contract rates" by sorting the multiple itinerary candidates in order of traveler satisfaction and contract rates estimated using the trained model. The itinerary generation unit 32b may identify (generate) multiple "itineraries estimated to have relatively high traveler satisfaction and contract rates."

[0047] As one variant, the itinerary generation unit 32b compares the number of people included in the travel conditions entered by the user (the number of people in a group of travelers) with a predetermined maximum number of people per group, and if the number of travelers (group) is greater than the maximum number, calculates the number of groups N by dividing the travelers into groups so that the number of people in each group is less than the maximum number, and then uses the learning model to redo the route search for the circular route in the itinerary identified (generated) to generate N new itineraries with different circular routes (itineraries in which the travelers travel in groups of N).

[0048] The itinerary output unit 32c outputs the itinerary generated by the itinerary generation unit 32b. For example, referring to FIG. 5, the itinerary output unit 32c may convert the generated itinerary into a character string in a natural language and output it in an interactive format in a dialogue area 51 within a display area 50 displayed on the terminal display unit 25. The itinerary output unit 32c may also output the generated itinerary on a timeline in a timeline area 52 within the display area 50 displayed on the terminal display unit 25. The itinerary output unit 32c may also output the generated itinerary on a map in a map area 53 within the display area 50 displayed on the terminal display unit 25.

[0049] 6, the itinerary output unit 32c may output a plurality of itineraries (10 patterns in the example shown in FIG. 6) generated by the itinerary generation unit 32b in the display area 50 displayed on the terminal display unit 25. The plurality of itineraries that are output may include an alternative plan that does not include the candidate location input by the user.

[0050] Referring to Figures 4 to 9, the area display unit 32d transmits a control signal to the terminal device 2 to display a display area 50 including a dialogue area 51, a timeline area 52, and a map area 53, and displays the display area 50 to the user via the terminal display unit 25.

[0051] 7, when a user inputs an instruction or question in a dialogue format in a dialogue region 51 in a display region 50 displayed on the terminal display unit 25, the region display unit 32d may convert the instruction or question input by the user into a prompt to be input to the dialogue AI, and then input the converted prompt to the dialogue AI. The search results output from the dialogue AI may be output in a dialogue format in the dialogue region 51 in the display region 50, or may be output on a timeline in the timeline region 52, or may be output on a map in the map region 53. For example, when an instruction such as "Please tell me about accommodations that are available for private hire" is input in the dialogue region 51, the region display unit 32d may convert the instruction or question into a prompt such as "Please tell me about accommodations that are available for private hire in Kanazawa" (identifying that the location of the accommodation is "Kanazawa," which is a candidate location for the travel conditions), and then input the converted prompt to the dialogue AI. Furthermore, if there is an agreed facility (a facility that has been tentatively reserved) with the travel agency in the candidate location of the travel conditions, the area display unit 32d may output the search results of the interactive AI by replacing the agreed facility with the travel agency. Also, for example, when an instruction to "List bus companies that are candidates for quotation requests" is input in the dialogue area 51, the area display unit 32d may format the instruction into a prompt such as "List five bus companies that are candidates for quotation requests and have Kanazawa as their business area" (identifying that the business area of ​​the bus company is "Kanazawa," which is the candidate location of the travel conditions), and then input the formatted prompt to the interactive AI.

[0052] 9 , when a specific spot is selected in the timeline area 52 or the map area 53 in the display area 50 displayed on the terminal display unit 25 and an incomplete (incomplete) character string as an instruction or question is input in a dialogue area 51 in the display area 50, the area display unit 32d may combine the character string input by the user with the spot name of the spot selected in the timeline area 52 or the map area 53 to form a prompt to be input to the dialogue AI. Specifically, for example, when "Omicho Market" is selected in the timeline area 52 or the map area 53 in the display area 50 and an incomplete (incomplete) instruction (an instruction in which it is unclear where the "surrounding area" is) such as "Tell me about tourist spots around Omicho Market" is input in the dialogue area 51, the area display unit 32d may form the prompt into "Tell me about tourist spots around Omicho Market" (specifying that the "surrounding area" is the area around "Omicho Market") and then input the formed prompt to the dialogue AI. The area display unit 32d may then output the search results (tourist spots around Omicho Market) output from the interactive AI in an interactive format in the interactive area 51 within the display area 50, or may output them on a map in the map area 51, although this is not shown.

[0053] The itinerary editing unit 32e acquires editing instructions that the user interactively inputs in the dialogue area 51 in the display area 50 displayed on the terminal display unit 25, and edits the itinerary generated by the itinerary generation unit 32b based on the editing instructions. For example, referring to Fig. 8, when the user operates the terminal input unit 24 to interactively input an editing instruction in the form of a character string in a natural language, such as "Change the plan to tour in three courses based on this itinerary," into the dialogue area 51 in the display area 50 displayed on the terminal display unit 25, the input character string is transmitted from the terminal device 2 to the server 3, and the itinerary editing unit 32e performs natural language processing on the received character string to identify the content of the editing instruction, and then re-runs a route search for the circular route in the current itinerary based on the editing instruction, thereby generating three new itineraries with different circular routes (editing the current itinerary into three new itineraries). The itinerary output unit 32c may output the itinerary edited in the itinerary editing unit 32e in an interactive format in an interaction area 51 in a display area 50 displayed on the terminal display unit 25, or may output it on a timeline in a timeline area 52, or may output it on a map in a map area 53.

[0054] The schedule generation unit 32f generates a schedule (task) for the travel agency at least up to the start date of the trip, based on the itinerary generated by the itinerary generation unit 32b (or the itinerary edited by the itinerary editing unit 32e). Specifically, for example, if the trip start date in the itinerary generated by the itinerary generation unit 32b (or the itinerary edited by the itinerary editing unit 32e) is October 1st, the schedule generation unit 32f may generate a schedule (task) for "making a final reservation at an accommodation" for February 1st, eight months prior to that date. The schedule generation unit 32f may further generate a schedule (task) for the travel agency from the start date of the trip onwards, in addition to the schedule (task) for the travel agency up to the start date of the trip, based on the itinerary generated by the itinerary generation unit 32b (or the itinerary edited by the itinerary editing unit 32e). The schedule generation unit 32f may send the generated schedule to the terminal device 2 and display it on a calendar screen (not shown) displayed on the terminal display unit 25, or may send it to the user's address using email, SMS, SNS, etc.

[0055] (Example of operation) Next, an example of the operation of the information processing system 1 configured as above will be described with reference to Fig. 2 and Fig. 4 to Fig. 9. Fig. 2 is a flowchart showing an example of the operation of the information processing system 1. Fig. 4 to Fig. 8 are diagrams showing examples of screens displayed by the information processing system 1.

[0056] Referring to Figures 2 and 4, first, the area display unit 32d of the server 3 transmits a control signal to the terminal device 2 to display a display area 50 including a dialogue area 51, a timeline area 52, and a map area 53, and displays the display area 50 to the user via the terminal display unit 25 (S10).

[0057] As shown in Figure 4, when a user operates the terminal input unit 24 to interactively input travel conditions (and traveler attributes) in a natural language string into the dialogue area 51 in the display area 50 displayed on the terminal display unit 25, the input string is sent from the terminal device 2 to the server 3, and the travel condition acquisition unit 32a of the server 3 performs natural language processing on the received string to identify and acquire the travel conditions (and traveler attributes) input by the user (step 20).

[0058] Next, the itinerary generation unit 32b uses a trained model that has been machine-learned using previously implemented itineraries and traveler satisfaction levels for those itineraries as training data to generate one or more itineraries that meet the travel conditions entered by the user and are estimated to have relatively high traveler satisfaction levels (step S30).

[0059] In step S30, the itinerary generation unit 32b may use a trained model that has been machine-learned using previously implemented itineraries, the satisfaction levels of travelers in those itineraries, and the attributes of those travelers as training data to generate one or more itineraries that satisfy the travel conditions input by the user and that are estimated to have a relatively high level of satisfaction for the attributes of the travelers input by the user.

[0060] In step S30, the itinerary generation unit 32b may use a trained model that has been machine-learned using itineraries created by travel agencies in the past, as well as the sales record for those itineraries and the satisfaction level of travelers for those itineraries as training data, to generate one or more itineraries that meet the travel conditions entered by the user and are estimated to have relatively high traveler satisfaction and sales success rates.

[0061] In step S30, the itinerary generation unit 32b may use a trained model that has been machine-learned using itineraries created by travel agencies in the past, the sales record for those itineraries, the satisfaction level of travelers on those itineraries, and the attributes of those travelers as training data to generate one or more itineraries that meet the travel conditions entered by the user and that are estimated to have relatively high satisfaction and sales success rates for the attributes of travelers entered by the user.

[0062] In step S30, if the number of people included in the travel conditions entered by the user (travel conditions acquired by the travel condition acquisition unit 32a) is greater than the predetermined maximum number of people per group, the itinerary generation unit 32b may divide the users into groups so that the number of people in each group is less than the maximum number of people, calculate the number of groups N, and then redo the route search for the circular route in the itinerary generated using the trained model to generate N new itineraries with different circular routes (itineraries in which the users travel in groups of N).

[0063] Next, itinerary output unit 32c outputs the itinerary generated by itinerary generation unit 32b (step S40). For example, referring to Fig. 5, itinerary output unit 32c converts the generated itinerary into a character string in a natural language and outputs it in an interactive format in an interaction area 51 in a display area 50 displayed on terminal display unit 25, outputs the generated itinerary on a timeline in a timeline area 52 in a display area 50 displayed on terminal display unit 25, and outputs the generated itinerary on a map in a map area 53 in a display area 50 displayed on terminal display unit 25.

[0064] When multiple itineraries are generated by the itinerary generation unit 32b, the itinerary output unit 32c may refer to Fig. 6 and output the multiple itineraries (10 patterns in the example shown in Fig. 6) generated by the itinerary generation unit 32b in the display area 50 displayed on the terminal display unit 25. The multiple itineraries that are output may include an alternative plan that does not include the candidate location input by the user.

[0065] In step S40, referring to Figure 7, when a user inputs instructions or questions in an interactive format in the dialogue area 51 in the display area 50 displayed on the terminal display unit 25, the area display unit 32d may format the instructions or questions input by the user into a prompt to be input to the dialogue AI, and then input the formatted prompt to the dialogue AI, and output the search results output from the dialogue AI in an interactive format in the dialogue area 51 in the display area 50. Also, referring to Figure 9, when a specific spot is selected in the timeline area 52 or map area 53 in the display area 50 displayed on the terminal display unit 25 and an insufficient (incomplete) string of characters as an instruction or question is input interactively in the dialogue area 51 in the display area 50, the area display unit 32d may combine the string of characters input by the user with the spot name of the spot selected in the timeline area 52 or map area 53 to form a prompt for input to the dialogue AI, and then input the formed prompt to the dialogue AI, and output the search results output from the dialogue AI interactively in the dialogue area 51 in the display area 50.

[0066] Next, the itinerary editing unit 32b determines whether or not the user has input an editing instruction in the dialogue area 51 in the display area 50 displayed on the terminal display unit 25 (step S50).

[0067] If an editing instruction has been input (step S50: YES), itinerary editing unit 32e acquires the editing instruction that the user has interactively input in dialogue area 51, and edits the itinerary generated by itinerary generation unit 32b based on the editing instruction (step S60). Then, itinerary output unit 32c outputs the itinerary edited by itinerary editing unit 32e to each of dialogue area 51, timeline area 52, and / or map area 53 in display area 50 displayed on terminal display unit 25 (step S40).

[0068] On the other hand, if no editing instruction has been input (step S50: NO), the schedule generation unit 32f generates a schedule (tasks) for the travel agency at least up to the start date of the trip, based on the itinerary generated by the itinerary generation unit 32b (or the itinerary edited by the itinerary editing unit 32e). The schedule generation unit 32f may send the generated schedule to the terminal device 2 and display it on a calendar screen (not shown) displayed on the terminal display unit 25, or may send it to the user's address using email, SMS, SNS, etc.

[0069] According to the present embodiment, by using a trained model that has been machine-learned using previously implemented itineraries and traveler satisfaction levels for those itineraries as training data, it is possible to generate itineraries that are estimated to have high traveler satisfaction levels based on the relationship between previously implemented itineraries and traveler satisfaction levels for those itineraries. This makes it possible to support travel agencies in creating itineraries that will have high traveler satisfaction levels, even if the sales representatives in charge of product planning at those agencies lack experience.

[0070] Furthermore, according to this embodiment, by using a trained model that has been machine-learned using itineraries previously created by a travel agency, the satisfaction levels of travelers for those itineraries, and the attributes of those travelers as training data, it is possible to generate itineraries that are estimated to have high satisfaction levels for specific traveler attributes based on the relationship between itineraries previously created by a travel agency and the satisfaction levels of travelers for those itineraries by attribute. This can help sales representatives in charge of product planning at travel agencies create itineraries that will provide higher satisfaction levels to present to customers.

[0071] Furthermore, according to this embodiment, by using a trained model that has been machine-learned using training data of itineraries created by travel agencies in the past, the sales record for those itineraries, and the satisfaction level of travelers for those itineraries, it is possible to generate itineraries that are estimated to have a high success rate and high satisfaction level based on the relationship between itineraries created by travel agencies in the past, the sales record for those itineraries, and the satisfaction level of travelers for those itineraries. This can help sales representatives in charge of product planning at travel agencies create itineraries with a high success rate and high satisfaction level to present to customers.

[0072] Furthermore, according to this embodiment, by using a trained model that has been machine-learned using training data of itineraries created by travel agencies in the past, the sales record for those itineraries, the satisfaction level of travelers for those itineraries, and the attributes of those travelers, it is possible to generate an itinerary that is estimated to have a high success rate and satisfaction level for specific traveler attributes based on the relationship between itineraries created by travel agencies in the past, the sales record for those itineraries, the satisfaction level of travelers for those itineraries, and the attributes of those travelers. This can help sales representatives in charge of product planning at travel agencies create itineraries with a higher success rate and higher satisfaction level to present to customers.

[0073] The configuration and operation (method) of the display area 50 including the dialogue area 51, timeline area 52, and map area 53 described in the above-mentioned embodiment is not limited to an aspect that uses a trained model that has been machine-learned using previously implemented itineraries and the satisfaction level of travelers in those itineraries as training data (i.e., an aspect that includes an itinerary generation unit 32b). In other words, in an information processing system (i.e., an information processing system that does not have an itinerary generation unit 32b) that does not use a learned model that has been machine-learned using previously implemented itineraries and traveler satisfaction levels for those itineraries as training data, when a user inputs instructions or questions in an interactive format in the dialogue area 51 in the display area 50 displayed on the terminal display unit 25, the area display unit 32d formats the instructions or questions input by the user into a prompt to be input to the dialogue AI, and then inputs the formatted prompt to the dialogue AI, and the search results output from the dialogue AI may be output in an interactive format in the dialogue area 51 in the display area 50, or may be output on a timeline in the timeline area 52 in the display area 50, or may be output on a map in the map area 53 in the display area 50.

[0074] In addition, in an information processing system (i.e., an information processing system that does not have an itinerary generation unit 32b) that does not use a trained model that has been machine-learned using previously implemented itineraries and traveler satisfaction levels for those itineraries as training data, when a specific spot is selected in the timeline area 52 or map area 53 within the display area 50 displayed on the terminal display unit 25 and an insufficient (incomplete) string of characters as an instruction or question is entered interactively in the dialogue area 51 within the display area 50, the area display unit 32d combines the string of characters entered by the user with the spot name of the spot selected in the timeline area 52 or map area 53 to form a prompt for input to the dialogue AI, and then inputs the formed prompt into the dialogue AI, and the search results output from the dialogue AI may be output interactively in the dialogue area 51 within the display area 50, or may be output on a timeline in the timeline area 52 within the display area 50, or may be output on a map in the map area 53 within the display area 50.

[0075] At least a part of the information processing system 1 described in the above embodiment may be configured with hardware or software. When configured with hardware, a program that realizes at least a part of the functions of the information processing system 1 may be stored on a recording medium such as a flexible disk or a CD-ROM, and may be read and executed by a computer. The recording medium is not limited to removable recording media such as magnetic disks and optical disks, but may also be fixed recording media such as hard disk drives and memories.

[0076] In addition, a program that realizes at least some of the functions of the information processing system 1 may be distributed via a communication line (including wireless communication) such as the Internet. Furthermore, the program may be encrypted, modulated, or compressed and distributed via a wired line or wireless line such as the Internet, or stored on a recording medium.

[0077] Furthermore, the information processing system 1 may be operated by one or more information processing devices. When multiple information processing devices are used, one of the information processing devices may be a computer, and the computer may execute a predetermined program to realize the functions of at least one means of the information processing system 1.

[0078] In the method invention, all processes (steps) may be realized by automatic control using a computer. Alternatively, each process may be performed by a computer, with progress control between processes being performed manually. Furthermore, at least some of the processes may be performed manually.

[0079] Based on the above description, a person skilled in the art may conceive additional effects and various modifications of the present invention, but the aspects of the present invention are not limited to the individual embodiments described above. Various additions, modifications, and partial deletions are possible within the scope of the conceptual idea and spirit of the present invention, which is derived from the content defined in the claims and their equivalents. [Explanation of symbols]

[0080] 1. Information Processing Systems 2. Terminal Device 21 Terminal communication unit 22 Terminal control unit 23 Terminal memory section 24 Terminal input section 25 Terminal display 3 Server 31 Server Communication Department 32 Server control unit 32a Travel condition acquisition section 32b Itinerary generator 32c Itinerary output section 32d area display section 32e Itinerary Editorial Department 32f Schedule generation section 33 Server storage unit 33a Route Network Information Database 33b Map information database 4 Network 50 display area 51 Dialogue Area 52 Timeline Area 53 Map Area

Claims

1. A means for acquiring travel conditions input by a user; A means for generating an itinerary that satisfies the travel conditions input by the user and is estimated to have a relatively high level of traveler satisfaction, using a machine-learned model that uses past itineraries and traveler satisfaction levels for those itineraries as training data; means for outputting the generated itinerary; An information processing system comprising:

2. The acquiring means further acquires attributes of the traveler input by the user; The generating means generates an itinerary that satisfies the travel conditions input by the user and is estimated to have a relatively high level of satisfaction for the traveler attributes input by the user, using a machine-learned model that uses previously implemented itineraries, traveler satisfaction levels for the itineraries, and traveler attributes as training data. The information processing system according to claim 1 .

3. The generating means generates an itinerary that satisfies the travel conditions input by the user and is estimated to have a relatively high traveler satisfaction rate and a relatively high success rate, using a machine-learned model that uses itineraries created by travel agencies in the past, as well as the sales record and traveler satisfaction rate for those itineraries as training data. The information processing system according to claim 1 .

4. The itinerary further includes information on events to be held during the trip and / or items to be provided during the trip in addition to information on locations and means of transportation.

4. The information processing system according to claim 1.

5. The itinerary is an itinerary generated between a travel agency and an operator, 4. The information processing system according to claim 1.

6. The generating means generates a plurality of itineraries that satisfy the travel conditions input by the user and are estimated to have a relatively high degree of traveler satisfaction; the output means outputs the generated itineraries.

4. The information processing system according to claim 1.

7. means for displaying to a user a display area including an interaction area, a timeline area, and a map area; the acquiring means acquires travel conditions inputted by the user in an interactive manner in the interactive area; The output means includes: outputting the generated itinerary in an interactive format in the interactive area; outputting the generated itinerary on a timeline in the timeline area; outputting the generated itinerary on a map in the map area; 4. The information processing system according to claim 1.

8. The system further includes a means for acquiring an editing instruction inputted by a user in an interactive manner in the interactive area, and editing the generated itinerary based on the editing instruction. The information processing system according to claim 7 .

9. The travel agency further comprises a means for generating a schedule for the travel agency at least up to the start date of the trip based on the generated itinerary.

4. The information processing system according to claim 1.

10. Computer, A means for acquiring travel conditions input by a user; A means for generating an itinerary that satisfies the travel conditions input by the user and is estimated to have a relatively high level of traveler satisfaction, using a machine-learned model that uses past itineraries and traveler satisfaction levels for those itineraries as training data; means for outputting the generated itinerary; An information processing program that functions as a

11. An information processing system configured by a plurality of computers connected to each other in a communicable manner, A means for acquiring travel conditions input by a user; A means for generating an itinerary that satisfies the travel conditions input by the user and is estimated to have a relatively high level of traveler satisfaction, using a machine-learned model that uses past itineraries and traveler satisfaction levels for those itineraries as training data; means for outputting the generated itinerary; In order to make the information processing system with An information processing program for causing at least one of the computers to function as at least one of the means.

12. In order to make the information processing system according to any one of claims 1 to 3 function using a plurality of computers connected in a communicable manner, An information processing program for causing at least one of the computers to function as at least one of the means in the information processing system according to any one of claims 1 to 3.

13. An information processing program for causing a computer to function as at least one of the means in the information processing system according to any one of claims 1 to 3.

14. 1. A computer-implemented information processing method, comprising: acquiring travel conditions input by a user; A step of generating an itinerary that satisfies the travel conditions input by the user and is estimated to have a relatively high level of traveler satisfaction, using a machine-learned model that uses past itineraries and traveler satisfaction levels for those itineraries as training data; outputting the generated itinerary; An information processing method including:

Images