Travel note generation method and device and electronic equipment

By determining tourism needs and note prompt content, combining the scenic spot information database, and using the travel note generation model to generate travel notes, the problems of high cost and difficult to unify the quality of travel notes in the existing technology are solved, and the generation efficiency and matching degree are improved.

CN119025588APending Publication Date: 2024-11-26BAIDU COM TIMES TECH (BEIJING) CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411132109.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

Existing travel notes are written manually by professional writers or senior tourists, and are costly and difficult to unify quality and style, and are inefficient in generation.

Method used

By determining tourism needs and note prompt content, combining the attraction information database, input the travel notes to generate matching travel notes, and train the model through training data to improve generation efficiency and quality.

Benefits of technology

It realizes the rapid generation of travel notes with unified quality and style, improves generation efficiency and matching, and reduces manual writing costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119025588A_ABST
    Figure CN119025588A_ABST
Patent Text Reader

Abstract

The invention provides a tourism note generation method and device and electronic equipment, and relates to the technical field of artificial intelligence, in particular to the technical fields of deep learning, natural language processing, large models and the like. The specific implementation scheme is as follows: determining a travel demand and travel note prompt content; determining tourism reference content corresponding to the tourism demand in combination with the tourism demand and the scenic spot information base; inputting the tourism demand, the tourism note prompt content and the tourism reference content into a tourism note generation model, and obtaining a tourism note corresponding to the tourism demand output by the tourism note generation model; in combination with the travel demand, the travel note prompt content, the travel reference content and the travel note generation model, the travel notes with uniform quality and style can be quickly generated, and the matching degree of the generated travel notes and the travel demand is relatively high, so that the generation efficiency of the travel notes is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to technical fields such as deep learning, natural language processing, and large models, and in particular to a travel notes generation method, device, and electronic device. Background Art

[0002] Current travel notes are manually written by professional writers or experienced tourists, which has high writing costs, makes it difficult to unify the quality and style of travel notes, and results in poor efficiency in generating travel notes. Summary of the invention

[0003] The present invention provides a travel note generation method, device and electronic device.

[0004] According to one aspect of the present disclosure, a travel notes generation method is provided, the method comprising: determining travel needs and travel notes prompt content; determining travel reference content corresponding to the travel needs in combination with the travel needs and a scenic spot information database; inputting the travel needs, the travel notes prompt content and the travel reference content into a travel notes generation model, and obtaining travel notes corresponding to the travel needs output by the travel notes generation model.

[0005] According to another aspect of the present disclosure, a method for training a travel notes generation model is provided, the method comprising: obtaining an initial travel notes generation model; obtaining training data; the training data comprising sample travel needs, sample travel notes prompt content, sample travel reference content and sample travel notes; training the initial travel notes generation model according to the sample travel needs, the sample travel notes prompt content, the sample travel reference content and the sample travel notes.

[0006] According to another aspect of the present disclosure, a travel notes generation device is provided, the device comprising: a first determination module, used to determine travel needs and travel notes prompt content; a second determination module, used to determine the travel reference content corresponding to the travel needs in combination with the travel needs and a scenic spot information database; a first acquisition module, used to input the travel needs, the travel notes prompt content and the travel reference content into a travel notes generation model, and acquire the travel notes corresponding to the travel needs output by the travel notes generation model.

[0007] According to another aspect of the present disclosure, a training device for a travel notes generation model is provided, the device comprising: a first acquisition module for acquiring an initial travel notes generation model; a second acquisition module for acquiring training data; the training data comprising sample travel needs, sample travel notes prompt content, sample travel reference content and sample travel notes; a training module for training the initial travel notes generation model according to the sample travel needs, the sample travel notes prompt content, the sample travel reference content and the sample travel notes.

[0008] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the travel notes generation method proposed above in the present disclosure; or, execute the training method of the travel notes generation model proposed above in the present disclosure.

[0009] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the travel notes generation method proposed above in the present disclosure; or, to execute the travel notes generation model training method proposed above in the present disclosure.

[0010] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the travel notes generation method proposed above in the present disclosure; or, implements the steps of the training method of the travel notes generation model proposed above in the present disclosure.

[0011] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0013] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;

[0014] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure;

[0015] Figure 3 is a schematic diagram according to a third embodiment of the present disclosure;

[0016] Figure 4This is a schematic diagram of travel notes generation;

[0017] Figure 5 is a schematic diagram according to a fourth embodiment of the present disclosure;

[0018] Figure 6 is a schematic diagram according to a fifth embodiment of the present disclosure;

[0019] Figure 7 is a schematic diagram according to a sixth embodiment of the present disclosure;

[0020] Figure 8 It is a block diagram of an electronic device used to implement the travel notes generation method or the travel notes generation model training method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0022] Current travel notes are manually written by professional writers or experienced tourists, which has high writing costs, makes it difficult to unify the quality and style of travel notes, and results in poor efficiency in generating travel notes.

[0023] In view of the above problems, the present disclosure proposes a travel notes generation method, device and electronic device.

[0024] Figure 1 This is a schematic diagram according to the first embodiment of the present disclosure. It should be noted that the travel note generation method of the embodiment of the present disclosure can be applied to a travel note generation device, which can be configured in an electronic device so that the electronic device can perform a travel note generation function. The following embodiments are described by taking the execution subject as an electronic device as an example.

[0025] Among them, the electronic device can be any device with computing capabilities, such as a personal computer (PC), a mobile terminal, a server, etc. The mobile terminal can be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, a smart speaker, a server, a server cluster, and other hardware devices with various operating systems, touch screens and / or display screens.

[0026] The travel note generation device may also be software in an electronic device, such as travel note generation software, etc. In the following embodiments, the travel note generation device is described as an electronic device.

[0027] like Figure 1 As shown, the travel notes generation method may include the following steps:

[0028] Step 101, determine travel needs and travel note reminder content.

[0029] In the embodiment of the present disclosure, the process of the electronic device determining tourism needs may, for example, include obtaining tourism demand text; extracting and processing the tourism demand text according to at least one tourism parameter item to obtain content under at least one tourism parameter item; and determining the tourism needs based on the content under at least one tourism parameter item.

[0030] The travel demand text may be preset, or the travel demand text may be provided to the object.

[0031] Wherein, when the travel demand text is pre-set, the pre-set travel demand text can be determined by combining the common travel demands of multiple objects. For example, when a large number of objects have travel demands for Beijing attractions, the travel demand text can be pre-set as "one-day tour in Beijing", etc., and the generated travel notes can be applicable to a large number of objects, that is, the generated travel notes can be pushed to a large number of objects.

[0032] When the travel demand text is provided by the object, the travel demand text may describe the personalized needs of the object, such as the object's travel destination, travel style, travel budget, etc. For example, the travel demand text provided by the object may be "a one-day relaxing tour in Beijing with a budget of 1,000 yuan".

[0033] The tourism parameter items may include at least one of the following: tourism destination, tourism duration, tourism budget, and tourism style. It should be noted that the contents of the tourism parameter items are not specifically limited here and can be adjusted according to actual needs.

[0034] Among them, the extraction of content under at least one tourism parameter item can accurately extract the required content from the tourism demand text, thereby improving the accuracy and comprehensiveness of the determined tourism demand; wherein the tourism parameter item can be flexibly adjusted, thereby improving the flexibility of the determined tourism demand.

[0035] In the disclosed embodiment, the travel note prompt content may include content prompts and rule prompts; the content prompts indicate the content that needs to be included in the travel notes; the rule prompts indicate the rules that need to be followed when generating travel notes.

[0036] The content prompt may be, for example, "You are an expert in making travel guides. Your task is to propose a detailed travel plan based on the information provided by users. Each scenic spot should include the tour route and sightseeing suggestions within the scenic spot." The rule prompt may be, for example, "1. Output the daily itinerary in a list format, separated by line breaks. 2. The introduction of each scenic spot should be specific, with detailed reasons for recommendation and internal tour routes, and the activity itinerary should be specific. 3. Include popular attractions and activities at the tourist destination, and reasonably plan the itinerary and attractions that can be visited according to the travel duration. 4. Consider the distance between attractions, and visit attractions with similar distances together to reduce travel time."

[0037] Among them, the settings of content prompts and rule prompts can reflect the content that needs to be included and the rules that need to be followed when generating travel notes, so as to determine the uniformity of the quality and style of the generated travel notes, thereby ensuring the quality and style of the generated travel notes. In addition, the content prompts and rule prompts can be adjusted according to actual needs to generate travel notes of different quality and style.

[0038] Step 102, combining the tourism demand and the scenic spot information database, determining the tourism reference content corresponding to the tourism demand.

[0039] In the disclosed embodiment, the tourism demand may include at least one content under a tourism parameter item. The electronic device may query the scenic spot information library according to the tourism demand to obtain the target scenic spot whose corresponding scenic spot information includes the content under each tourism parameter item; and determine the scenic spot information of the target scenic spot as the tourism reference content corresponding to the tourism demand.

[0040] Step 103: input the travel demand, travel note prompt content and travel reference content into the travel note generation model, and obtain the travel notes corresponding to the travel demand output by the travel note generation model.

[0041] In the disclosed embodiment, the travel notes generation model can be deployed in an electronic device; or, the travel notes generation model can be deployed in other devices that communicate with the electronic device. Where the travel notes generation model is deployed in an electronic device, the electronic device can call the travel notes generation model deployed by itself to obtain travel notes corresponding to travel needs. Where the travel notes generation model is deployed in other devices that communicate with the electronic device, the electronic device can send a model call request to the other device to obtain travel notes output by the travel notes generation model in the other electronic device.

[0042] In the disclosed embodiment, after step 103, the electronic device may further perform the following process: obtaining non-text content matching the travel notes; and updating the travel notes according to the non-text content. The non-text content may be, for example, images, charts, audio, video, animation, links, etc., which may be set according to actual needs.

[0043] It should be noted that the travel notes output by the travel notes generation model contain text content. Specifically, in order to improve the richness of the travel notes, the electronic device can determine at least one non-text content such as pictures, videos or audios that matches the content of the partial paragraph text, and then insert the at least one non-text content into the travel notes. In addition, the electronic device can also determine the relevant explanatory web pages of some concepts, and bind the links of the relevant explanatory web pages to the partial concepts. In addition, the electronic device can also mark the key content in the travel notes in yellow, bold, etc.

[0044] In the embodiment of the present disclosure, after step 103, the electronic device may also perform the following process: push the travel notes to at least one object; upon obtaining feedback content on the travel notes from at least one object, provide the travel notes and the feedback content on the travel notes to a deployment device or training device of a travel notes generation model for fine-tuning the travel notes generation model.

[0045] The travel notes generation method of the disclosed embodiment determines travel needs and travel notes prompt content; determines travel reference content corresponding to the travel needs in combination with the travel needs and a scenic spot information database; inputs the travel needs, travel notes prompt content and travel reference content into a travel notes generation model, and obtains travel notes corresponding to the travel needs output by the travel notes generation model; wherein, by combining the travel needs, travel notes prompt content, travel reference content and the travel notes generation model, travel notes with uniform quality and style can be quickly generated, and the generated travel notes have a high degree of matching with the travel needs, thereby improving the generation efficiency of travel notes.

[0046] In order to further improve the matching degree between the generated travel notes and the travel needs, and further improve the accuracy of the generated travel notes, the scenic spot information matching the travel needs in the scenic spot information database can be used as the travel reference content. Figure 2 As shown, Figure 2 is a schematic diagram according to a second embodiment of the present disclosure, Figure 2 The illustrated embodiment may include the following steps:

[0047] Step 201, determine travel needs and travel note reminder content.

[0048] Step 202: query the scenic spot information database according to the tourism demand, and obtain the scenic spot information matching the tourism demand in the scenic spot information database.

[0049] In the disclosed embodiment, the tourism demand may include content under at least one tourism parameter item. The scenic spot information matching the tourism demand in the scenic spot information database may include at least one of the following: scenic spot information including content under all tourism parameter items in the tourism demand; scenic spot information including content under some tourism parameter items in the tourism demand; scenic spot information having a semantic similarity with content under some tourism parameter items greater than or equal to a preset similarity threshold; scenic spot information having a semantic similarity with content under all tourism parameter items greater than or equal to a preset similarity threshold.

[0050] Step 203: determine the scenic spot information matching the tourism demand in the scenic spot information database as the tourism reference content corresponding to the tourism demand.

[0051] In the disclosed embodiment, in order to further expand the tourism reference content, expand the content referenced when generating travel notes, and further improve the matching degree between the generated travel notes and tourism needs, the electronic device can also perform the following process: query the travel notes library according to the tourism needs, and obtain the first historical travel notes in the travel notes library that match the tourism needs; determine the first historical travel notes and / or the scenic spot information referenced when generating the first historical travel notes as the tourism reference content corresponding to the tourism needs.

[0052] Among them, the first historical travel notes matching the tourism demand may include at least one of the following: historical travel notes including the contents under each tourism parameter item in the tourism demand; historical travel notes including the contents under some tourism tree items in the tourism demand.

[0053] In the disclosed embodiment, in order to ensure that the generated travel notes are travel notes that the provider of travel needs is interested in, ensure that the generated travel notes are travel notes required by the provider, and further improve the efficiency of travel note generation, the electronic device can also perform the following process: obtain the second historical travel notes collected by the provider of travel needs; determine the second historical travel notes and / or the scenic spot information referenced when generating the second historical travel notes as travel reference content corresponding to the travel needs.

[0054] In the disclosed embodiment, in order to further expand the tourism reference content and improve the matching degree between the generated travel notes and the tourism needs, the electronic device may also perform the following process: obtaining historical tourism needs that match the tourism needs; and determining the travel notes corresponding to the historical tourism needs as the tourism reference content corresponding to the tourism needs.

[0055] Among them, it should be noted that, based on the above embodiments, the electronic device can determine at least one of the following as the tourism reference content corresponding to the tourism demand: scenic spot information matching the tourism demand in the scenic spot information library; the first historical travel notes matching the tourism demand in the travel notes library; the scenic spot information referenced when the first historical travel notes are generated; the second historical travel notes collected by the provider of the tourism demand; the scenic spot information referenced when the second historical travel notes are generated; and the travel notes corresponding to the historical tourism demand matching the tourism demand.

[0056] Step 204: input the travel demand, travel note prompt content and travel reference content into the travel note generation model, and obtain the travel notes corresponding to the travel demand output by the travel note generation model.

[0057] It should be noted that the details of step 201 and step 204 can be found in Figure 1 Step 101 and step 103 in the illustrated embodiment will not be described in detail herein.

[0058] The tourist note generation method of the embodiment of the present disclosure determines the tourist demand and the tourist note prompt content; queries the scenic spot information database according to the tourist demand to obtain the tourist spot information matching the tourist demand in the scenic spot information database; determines the tourist spot information matching the tourist demand in the scenic spot information database as the tourist reference content corresponding to the tourist demand; inputs the tourist demand, the tourist note prompt content and the tourist reference content into the tourist note generation model to obtain the tourist notes corresponding to the tourist demand output by the tourist note generation model; wherein, performing tourist note generation processing in combination with the tourist spot information matching the tourist demand in the scenic spot information database can improve the matching degree between the generated tourist notes and the tourist demand, and further improve the accuracy of the generated tourist notes.

[0059] In order to further improve the accuracy of the tourist reference content used in the generated tourist notes, the tourist attraction information database can be generated by combining the tourist attractions in the map and at least one tourist attraction data source, and then the tourist reference content can be determined by combining the generated tourist attraction information database. Figure 3 As shown, Figure 3 is a schematic diagram according to a third embodiment of the present disclosure, Figure 3 The illustrated embodiment may include the following steps:

[0060] Step 301, obtaining multiple scenic spots in the map.

[0061] In the disclosed embodiment, the electronic device can obtain the names and addresses of multiple scenic spots from the map. The multiple scenic spots in the map can be points of interest of the type of tourist attractions in the map.

[0062] Step 302: for each scenic spot, capture scenic spot data related to the scenic spot from at least one scenic spot data source.

[0063] In the disclosed embodiment, the source of scenic spot data may include at least one of the following: travel-related software, scenic spot ticket-related software, scenic spot route planning-related software, scenic spot recommendation-related software, etc., which may be set according to actual needs.

[0064] Among them, scenic spot data related to scenic spots, such as scenic spot route planning data, scenic spot ticket data, scenic spot recommendation data, scenic spot evaluation data, travel agency data, etc., can be set according to actual needs.

[0065] Step 303: extract and understand the scenic spot data to obtain the scenic spot information.

[0066] In the disclosed embodiment, the process of the electronic device executing step 303 may be, for example, performing sentiment analysis on the scenic spot data to obtain a sentiment analysis result; when the sentiment analysis result is positive, performing scenic spot information extraction and understanding processing on the scenic spot data to obtain scenic spot information of the scenic spot.

[0067] Among them, when the sentiment analysis result of the scenic spot data is negative, the scenic spot data is ignored. In addition, in order to ensure the comprehensiveness of the scenic spot information, when the sentiment analysis result of the scenic spot data is neutral, the scenic spot data can also be processed for scenic spot information extraction and understanding to obtain the scenic spot information of the scenic spot.

[0068] Among them, combining the scenic spot data with positive sentiment analysis results to determine the scenic spot information of the scenic spot, and avoiding combining the scenic spot data with negative sentiment analysis results to determine the scenic spot information of the scenic spot, can ensure the quality of the scenic spot information in the scenic spot information database, and further ensure the positivity of the generated travel notes.

[0069] In the disclosed embodiment, the scenic spot data may include data in various forms, such as text, images, charts, audio, video, animation, etc. Among them, the process of the electronic device extracting and understanding the scenic spot data may be, for example, extracting the non-text data in the scenic spot data to extract the text therein; for the text, when the number of characters in the text is less than or equal to the preset number threshold, combining the customized natural language processing (Natural Language Processing Customization, NLPC) to perform entity recognition processing on the text; when the number of characters in the text is greater than the preset number threshold, combining the text processing model to perform entity recognition, keyword extraction, introduction extraction, etc. on the text.

[0070] Step 304: Determine a scenic spot information database based on the scenic spot information of the plurality of scenic spots.

[0071] In the disclosed embodiment, the scenic spot information of the scenic spot may include at least one of the following: scenic spot name, scenic spot address, scenic spot introduction, scenic spot opening hours, scenic spot visiting time, projects in the scenic spot, transportation near the scenic spot, accommodation near the scenic spot, catering near the scenic spot, etc., which can be set according to actual needs and are not specifically limited here.

[0072] Step 305, determining travel needs and travel note reminder content.

[0073] Step 306, combining the tourism demand and the scenic spot information database, determining the tourism reference content corresponding to the tourism demand.

[0074] Step 307: input the travel demand, travel note prompt content and travel reference content into the travel note generation model, and obtain the travel notes corresponding to the travel demand output by the travel note generation model.

[0075] It should be noted that the details of steps 305 to 307 can be found in Figure 1 Steps 101 to 103 in the illustrated embodiment will not be described in detail herein.

[0076] The tourist note generation method of the embodiment of the present disclosure obtains multiple tourist attractions in a map; for each tourist attraction, captures tourist attraction data related to the tourist attraction from at least one tourist attraction data source; extracts and understands the tourist attraction data to obtain tourist attraction information of the tourist attraction; determines a tourist attraction information library based on the tourist attraction information of the multiple tourist attractions; determines tourist demand and tourist note prompt content; determines tourist reference content corresponding to the tourist demand in combination with the tourist demand and the tourist note information library; inputs the tourist demand, the tourist note prompt content and the tourist reference content into a tourist note generation model, and obtains tourist notes corresponding to the tourist demand output by the tourist note generation model; wherein, the tourist attraction information library is generated in combination with the tourist attractions in the map and at least one tourist attraction data source, and then the tourist reference content is determined in combination with the generated tourist attraction information library for use in the tourist note generation process, which can further improve the accuracy of the generated tourist notes.

[0077] The following examples are used to illustrate this. Figure 4 The following is a schematic diagram of travel notes generation. Figure 4The following steps may be included. Step 401, obtain POI information from maps and multiple sources and aggregate and format it to obtain a POI attraction library (i.e., attraction information library). Step 402, obtain prompt (travel note prompt content) + query (travel demand); combine query and retrieval method (inverse retrieval, approximate nearest neighbor ANN retrieval), etc. to obtain retrieval results (travel reference content) from the POI attraction library. Step 403, input prompt+query+retrieval results into the tourism vertical model (travel note generation model) to obtain a complete guide (i.e., travel notes). Step 404, combine the complete guide and the personalized customization (new travel demand) provided by the Actor (i.e., object) to generate a new complete guide (which may include note title, note content, pictures, voice, etc.).

[0078] Figure 5 It is a schematic diagram according to the fourth embodiment of the present disclosure. It should be noted that the training method of the travel note generation model of the embodiment of the present disclosure can be applied to the training device of the travel note generation model, and the device can be configured in an electronic device so that the electronic device can perform the training function of the travel note generation model. In the following embodiments, the execution subject is an electronic device as an example for explanation.

[0079] Among them, the electronic device can be any device with computing capabilities, such as a personal computer (PC), a mobile terminal, a server, etc. The mobile terminal can be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, a smart speaker, a server, a server cluster, and other hardware devices with various operating systems, touch screens and / or display screens.

[0080] The training device for the travel notes generation model may also be software in an electronic device, such as training software for the travel notes generation model, etc. In the following embodiments, the training device for the travel notes generation model is an electronic device as an example for description.

[0081] like Figure 5 As shown, the travel notes generation method may include the following steps:

[0082] Step 501, obtaining an initial travel notes generation model.

[0083] In the disclosed embodiment, the travel notes generation model may be a pre-trained text generation model, wherein the text generation model may be, for example, a recurrent neural network model, a long short-term memory network model, etc., which may be set according to actual needs.

[0084] Step 502, obtaining training data; the training data includes sample travel needs, sample travel note prompt content, sample travel reference content and sample travel notes.

[0085] In the disclosed embodiment, the sample travel demand may include content under at least one travel parameter item, wherein the travel parameter item may include at least one of the following: travel destination, travel duration, travel budget, and travel style.

[0086] In the disclosed embodiment, the sample travel note prompt content may include content prompts and rule prompts; the content prompts indicate the content that needs to be included in the travel notes; the rule prompts indicate the rules that need to be followed when generating travel notes.

[0087] Step 503, training the initial travel notes generation model according to the sample travel needs, the sample travel notes prompt content, the sample travel reference content and the sample travel notes.

[0088] In the disclosed embodiment, the process of the electronic device executing step 503 may, for example, be: inputting sample travel needs, sample travel notes prompt content, and sample travel reference content into an initial travel notes generation model to obtain predicted travel notes output by the travel notes generation model; combining the predicted travel notes, sample travel notes, and the loss function of the travel notes generation model to determine the value of the loss function; and adjusting the parameters of the travel notes generation model based on the value of the loss function to obtain a trained travel notes generation model.

[0089] In the disclosed embodiment, after step 503, the electronic device may also perform the following process: obtaining the travel notes generated by the trained travel notes generation model and the feedback content corresponding to the travel notes; and fine-tuning the travel notes generation model in combination with the travel notes and the feedback content corresponding to the travel notes.

[0090] The feedback content corresponding to the travel notes includes, for example, positive feedback, negative feedback, etc. The travel notes generation model is fine-tuned in combination with the feedback content corresponding to the travel notes, so that the travel notes generation model can be updated in real time, thereby improving the accuracy of the travel notes generation model.

[0091] The training method of the travel note generation model of the embodiment of the present disclosure is as follows: obtaining an initial travel note generation model; obtaining training data; the training data includes sample travel needs, sample travel note prompt content, sample travel reference content and sample travel notes; training the initial travel note generation model according to the sample travel needs, sample travel note prompt content, sample travel reference content and sample travel notes, so as to obtain a travel note generation model for travel note generation processing, thereby improving the generation efficiency of travel notes.

[0092] In order to implement the above embodiment, the present disclosure also provides a travel note generating device. Figure 6 As shown, Figure 6 The travel note generating device 60 may include: a first determining module 601 , a second determining module 602 , and a first obtaining module 603 .

[0093] Among them, the first determination module 601 is used to determine the travel needs and the travel notes prompt content; the second determination module 602 is used to determine the travel reference content corresponding to the travel needs in combination with the travel needs and the scenic spot information database; the first acquisition module 603 is used to input the travel needs, the travel notes prompt content and the travel reference content into the travel notes generation model, and obtain the travel notes corresponding to the travel needs output by the travel notes generation model.

[0094] As a possible implementation method of the embodiment of the present disclosure, the second determination module 602 is specifically used to query the scenic spot information database according to the tourism needs, obtain the scenic spot information in the scenic spot information database that matches the tourism needs; and determine the scenic spot information in the scenic spot information database that matches the tourism needs as the tourism reference content corresponding to the tourism needs.

[0095] As a possible implementation method of the embodiment of the present disclosure, the device also includes: a second acquisition module and a third determination module; the second acquisition module is used to query the travel notes library according to the travel needs, and obtain the first historical travel notes in the travel notes library that match the travel needs; the third determination module is used to determine the first historical travel notes and / or the scenic spot information referenced when generating the first historical travel notes as the travel reference content corresponding to the travel needs.

[0096] As a possible implementation method of the embodiment of the present disclosure, the device also includes: a third acquisition module and a fourth determination module; the third acquisition module is used to acquire the second historical travel notes collected by the provider of the tourism demand; the fourth determination module is used to determine the second historical travel notes and / or the scenic spot information referenced when generating the second historical travel notes as the tourism reference content corresponding to the tourism demand.

[0097] As a possible implementation method of the embodiment of the present disclosure, the device also includes: a fourth acquisition module and a fifth determination module; the fourth acquisition module is used to acquire historical travel needs that match the travel needs; the fifth determination module is used to determine the travel notes corresponding to the historical travel needs as the travel reference content corresponding to the travel needs.

[0098] As a possible implementation method of the embodiment of the present disclosure, a method for determining the scenic spot information database includes: obtaining multiple scenic spots in a map; for each scenic spot, capturing scenic spot data related to the scenic spot from at least one scenic spot data source; performing information extraction and understanding processing on the scenic spot data to obtain scenic spot information of the scenic spot; and determining the scenic spot information database based on the scenic spot information of the multiple scenic spots.

[0099] As a possible implementation method of an embodiment of the present disclosure, a method for determining scenic spot information in the scenic spot information database includes: performing sentiment analysis on the scenic spot data to obtain a sentiment analysis result; when the sentiment analysis result is positive, performing scenic spot information extraction and understanding processing on the scenic spot data to obtain the scenic spot information of the scenic spot.

[0100] As a possible implementation method of the embodiment of the present disclosure, the first determination module 601 is specifically used to obtain a tourism demand text; extract and process the tourism demand text according to at least one tourism parameter item to obtain the content under the at least one tourism parameter item; and determine the tourism demand based on the content under the at least one tourism parameter item.

[0101] As a possible implementation method of the embodiment of the present disclosure, the travel note prompt content includes content prompts and rule prompts; the content prompts indicate the content that needs to be included in the travel notes; the rule prompts indicate the rules that need to be followed when generating travel notes.

[0102] As a possible implementation method of the embodiment of the present disclosure, the device also includes: a fifth acquisition module and an update processing module; the fifth acquisition module is used to acquire non-text content matching the travel notes; the update processing module is used to update the travel notes according to the non-text content.

[0103] The travel note generation device of the embodiment of the present disclosure determines travel needs and travel note prompt content; determines travel reference content corresponding to the travel needs in combination with the travel needs and the scenic spot information database; inputs the travel needs, travel note prompt content and travel reference content into a travel note generation model, and obtains travel notes corresponding to the travel needs output by the travel note generation model; wherein, by combining the travel needs, travel note prompt content, travel reference content and the travel note generation model, travel notes with uniform quality and style can be quickly generated, and the generated travel notes have a high degree of matching with the travel needs, thereby improving the generation efficiency of the travel notes.

[0104] In order to implement the above embodiment, the present disclosure also provides a training device for a travel notes generation model. Figure 7 As shown, Figure 7 70 is a schematic diagram of the sixth embodiment of the present disclosure. The travel notes generation model training device 70 may include: a first acquisition module 701 , a second acquisition module 702 and a training module 703 .

[0105] Among them, the first acquisition module 701 is used to obtain the initial travel notes generation model; the second acquisition module 702 is used to obtain training data; the training data includes sample travel needs, sample travel notes prompt content, sample travel reference content and sample travel notes; the training module 703 is used to train the initial travel notes generation model according to the sample travel needs, the sample travel notes prompt content, the sample travel reference content and the sample travel notes.

[0106] As a possible implementation method of the embodiment of the present disclosure, the device also includes: a third acquisition module and a fine-tuning processing module; the third acquisition module is used to acquire the travel notes generated by the trained travel notes generation model and the feedback content corresponding to the travel notes; the fine-tuning processing module is used to fine-tune the travel notes generation model in combination with the travel notes and the feedback content corresponding to the travel notes.

[0107] The training device of the travel note generation model of the embodiment of the present disclosure obtains an initial travel note generation model; obtains training data; the training data includes sample travel needs, sample travel note prompt content, sample travel reference content and sample travel notes; the initial travel note generation model is trained according to the sample travel needs, sample travel note prompt content, sample travel reference content and sample travel notes, so as to obtain a travel note generation model for travel note generation processing, thereby improving the generation efficiency of travel notes.

[0108] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information are all carried out with the user's consent, comply with the relevant laws and regulations, and do not violate public order and good morals.

[0109] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0110] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0111] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0112] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0113] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as a tourist note generation method or a training method for a tourist note generation model. For example, in some embodiments, the tourist note generation method or the training method for a tourist note generation model may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the tourist note generation method or the training method for the tourist note generation model described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the travel notes generation method or the travel notes generation model training method in any other appropriate manner (for example, by means of firmware).

[0114] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0115] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0116] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0117] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0118] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0119] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0120] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0121] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating travel notes, the method comprising: Determine travel needs and travel notes; Determine the tourism reference content corresponding to the tourism demand in combination with the scenic spot information database; The travel demand, the travel note prompt content and the travel reference content are input into a travel note generation model, and the travel notes corresponding to the travel demand output by the travel note generation model are obtained.

2. The method according to claim 1, wherein: The step of combining the tourism demand and the scenic spot information database to determine the tourism reference content corresponding to the tourism demand includes: Query the scenic spot information database according to the travel demand, and obtain the scenic spot information matching the travel demand in the scenic spot information database; The scenic spot information matching the tourism demand in the scenic spot information database is determined as the tourism reference content corresponding to the tourism demand.

3. The method according to claim 1 or 2, wherein: The method further comprises: Querying a travel note library according to the travel demand, and obtaining a first historical travel note in the travel note library that matches the travel demand; The first historical travel note and / or the scenic spot information referred to when generating the first historical travel note are determined as the travel reference content corresponding to the travel demand.

4. The method according to claim 1 or 2, wherein: The method further comprises: Acquire a second historical travel note collected by the provider of the travel demand; The second historical travel notes and / or the scenic spot information referred to when generating the second historical travel notes are determined as the travel reference content corresponding to the travel demand.

5. The method according to claim 1 or 2, wherein: The method further comprises: Acquire historical tourism demand matching the tourism demand; The travel notes corresponding to the historical travel needs are determined as travel reference content corresponding to the travel needs.

6. The method according to claim 1, wherein: The method for determining the scenic spot information database includes: Get multiple attractions in the map; For each scenic spot, crawling scenic spot data related to the scenic spot from at least one scenic spot data source; Extracting and understanding the scenic spot data to obtain scenic spot information of the scenic spot; The scenic spot information database is determined according to the scenic spot information of the plurality of scenic spots.

7. The method according to claim 6, wherein: The extracting and understanding the scenic spot data to obtain the scenic spot information of the scenic spot includes: Performing sentiment analysis on the scenic spot data to obtain sentiment analysis results; When the sentiment analysis result is positive, scenic spot information extraction and understanding processing are performed on the scenic spot data to obtain scenic spot information of the scenic spot.

8. The method according to claim 1, wherein: The method for determining the tourism demand includes: Get travel demand text; Extracting and processing the tourism demand text according to at least one tourism parameter item to obtain content under the at least one tourism parameter item; The tourism demand is determined according to the content under the at least one tourism parameter item.

9. The method according to claim 1, wherein: The travel notes prompt content includes content prompts and rule prompts; The content prompt indicates the content that needs to be included in the travel notes; The rule prompt indicates the rules that need to be followed when generating travel notes.

10. The method according to claim 1, wherein: The method further comprises: Obtaining non-text content matching the travel note; The travel notes are updated according to the non-text content.

11. A method for training a travel notes generation model, the method comprising: Obtain an initial travel notes generation model; Get training data; The training data includes sample travel needs, sample travel note prompts, sample travel references and sample travel notes; The initial travel notes generation model is trained according to the sample travel needs, the sample travel notes prompt content, the sample travel reference content and the sample travel notes.

12. The method according to claim 11, wherein: The method further comprises: Obtain travel notes generated by a trained travel notes generation model and feedback content corresponding to the travel notes; The travel notes generation model is fine-tuned based on the travel notes and the feedback content corresponding to the travel notes.

13. A travel notes generating device, comprising: The first determination module is used to determine the travel needs and the travel notes reminder content; A second determination module is used to determine the tourism reference content corresponding to the tourism demand in combination with the tourism demand and the scenic spot information database; The first acquisition module is used to input the travel demand, the travel note prompt content and the travel reference content into a travel note generation model, and obtain the travel notes corresponding to the travel demand output by the travel note generation model.

14. The device according to claim 13, wherein: The second determination module is specifically configured to: Query the scenic spot information database according to the travel demand, and obtain the scenic spot information matching the travel demand in the scenic spot information database; The scenic spot information matching the tourism demand in the scenic spot information database is determined as the tourism reference content corresponding to the tourism demand.

15. The device according to claim 13 or 14, wherein: The device further comprises: a second acquisition module and a third determination module; The second acquisition module is used to query the travel notes library according to the travel demand, and acquire the first historical travel notes matching the travel demand in the travel notes library; The third determination module is used to determine the first historical travel notes and / or the scenic spot information referenced when generating the first historical travel notes as the travel reference content corresponding to the travel demand.

16. The device according to claim 13 or 14, wherein: The device further comprises: a third acquisition module and a fourth determination module; The third acquisition module is used to acquire the second historical travel notes collected by the provider of the travel demand; The fourth determination module is used to determine the second historical travel notes and / or the scenic spot information referenced when generating the second historical travel notes as the travel reference content corresponding to the travel demand.

17. The device according to claim 13 or 14, wherein: The device further includes: a fourth acquisition module and a fifth determination module; The fourth acquisition module is used to acquire historical tourism demands matching the tourism demands; The fifth determining module is used to determine the travel notes corresponding to the historical travel needs as the travel reference content corresponding to the travel needs.

18. The device according to claim 13, wherein: The method for determining the scenic spot information database includes: Get multiple attractions in the map; For each scenic spot, crawling scenic spot data related to the scenic spot from at least one scenic spot data source; Extracting and understanding the scenic spot data to obtain scenic spot information of the scenic spot; The scenic spot information database is determined according to the scenic spot information of the plurality of scenic spots.

19. The device according to claim 18, wherein: The method for determining the scenic spot information in the scenic spot information database includes: Performing sentiment analysis on the scenic spot data to obtain sentiment analysis results; When the sentiment analysis result is positive, scenic spot information extraction and understanding processing are performed on the scenic spot data to obtain scenic spot information of the scenic spot.

20. The device according to claim 13, wherein: The first determination module is specifically configured to: Get travel demand text; Extracting and processing the tourism demand text according to at least one tourism parameter item to obtain content under the at least one tourism parameter item; The tourism demand is determined according to the content under the at least one tourism parameter item.

21. The device according to claim 13, wherein: The travel notes prompt content includes content prompts and rule prompts; The content prompt indicates the content that needs to be included in the travel notes; The rule prompt indicates the rules that need to be followed when generating travel notes.

22. The device according to claim 13, wherein: The device further comprises: a fifth acquisition module and an update processing module; The fifth acquisition module is used to acquire non-text content matching the travel notes; The update processing module is used to update the travel notes according to the non-text content.

23. A training device for a travel notes generation model, the device comprising: The first acquisition module is used to acquire an initial travel notes generation model; A second acquisition module is used to acquire training data; The training data includes sample travel needs, sample travel note prompts, sample travel references and sample travel notes; The training module is used to train the initial travel notes generation model according to the sample travel needs, the sample travel notes prompt content, the sample travel reference content and the sample travel notes.

24. The device according to claim 23, wherein: The device further comprises: a third acquisition module and a fine-tuning processing module; The third acquisition module is used to acquire the travel notes generated by the trained travel notes generation model and the feedback content corresponding to the travel notes; The fine-tuning processing module is used to fine-tune the travel notes generation model in combination with the travel notes and the feedback content corresponding to the travel notes.

25. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10; Alternatively, the method according to any one of claims 11 to 12 is performed.

26. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 10; or to execute the method according to any one of claims 11 to 12.

27. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 10; or implements the method according to any one of claims 11 to 12.

Citation Information

Patent Citations

  • Automatic generation method and system of self-driving travel road book

    CN117520652A

  • Smart tourism system based on large model

    CN118410987A