CN117556155A - Stroke planning method, device, equipment and storage medium based on large language model - Google Patents
Stroke planning method, device, equipment and storage medium based on large language model Download PDFInfo
- Publication number
- CN117556155A CN117556155A CN202311555179.2A CN202311555179A CN117556155A CN 117556155 A CN117556155 A CN 117556155A CN 202311555179 A CN202311555179 A CN 202311555179A CN 117556155 A CN117556155 A CN 117556155A
- Authority
- CN
- China
- Prior art keywords
- information
- journey
- travel
- planning
- destination
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 81
- 230000003993 interaction Effects 0.000 claims abstract description 45
- 238000012790 confirmation Methods 0.000 claims abstract description 28
- 230000008447 perception Effects 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims description 18
- 230000006399 behavior Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 10
- 238000012986 modification Methods 0.000 claims description 8
- 230000004048 modification Effects 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 19
- 238000010586 diagram Methods 0.000 description 13
- 239000008186 active pharmaceutical agent Substances 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 238000001514 detection method Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 5
- 230000004308 accommodation Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 230000002452 interceptive effect Effects 0.000 description 4
- 238000010295 mobile communication Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 235000006694 eating habits Nutrition 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000010006 flight Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008929 regeneration Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010897 surface acoustic wave method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/02—Reservations, e.g. for tickets, services or events
- G06Q10/025—Coordination of plural reservations, e.g. plural trip segments, transportation combined with accommodation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a journey planning method, a journey planning device, electronic equipment and a storage medium based on a large language model, wherein the journey planning method comprises the following steps: receiving an input trip planning request, acquiring user information and interaction information associated with the trip planning, and determining a destination for carrying out the trip planning according to the user information and the interaction information, wherein the user information comprises user portraits, historical behavior data and scene perception data; generating travel content and displaying the travel content according to the destination and the user information by using a large language model; and under the condition that a confirmation instruction input based on the journey content is received, obtaining a journey planning task list according to the confirmation instruction, and displaying the journey planning task list according to a list display rule. The method and the device realize accurate planning of the journey according to the user portrait, the historical behavior data and the scene perception data in the journey planning process, can more accurately obtain the journey planning meeting the user requirements, and improve the accuracy and the rationality of the journey planning.
Description
Technical Field
The present disclosure relates to the field of trip planning technologies, and in particular, to a trip planning method, apparatus, electronic device, and storage medium based on a large language model.
Background
With the rise of living standard, travel has gradually evolved into an indispensable leisure and relaxation mode in people's life. Whether it is leisure vacation or business trip, the need for a personalized, efficient, seamless trip planning experience is becoming more urgent. Itinerary planning refers to the process of planning activities and scheduling in an itinerary by a user according to his own needs, preferences, time constraints, budgets, etc. before traveling or going out. It relates to destination selection, traffic mode selection and reservation, accommodation selection and reservation, and scenic spot visit in the journey, experience activity arrangement, etc. Trip planning is intended to ensure that users are able to take full advantage of limited time and resources to achieve an optimal travel experience.
Traditional journey planning mainly takes a manual arrangement mode as a main mode, and relies on personal experience, knowledge and the like to match and recommend journey contents, so that the journey contents can be wrong or inaccurate in matching, and actual journey experience is affected, for example, the journey planning mode based on a predefined rule and a recommendation model can lead to inaccurate knowledge of actual demands of different users due to limitation of the rule and limitation of a model training sample, and further cause inaccurate recommendation of journey.
Disclosure of Invention
An object of the embodiments of the present application is to provide a trip planning method, apparatus, electronic device and storage medium based on a large language model, so as to solve a technical problem of inaccurate trip planning in a related technology.
In a first aspect, an embodiment of the present application provides a trip planning method based on a large language model, including:
receiving an input trip planning request, acquiring user information and interaction information associated with the trip planning, and determining a destination for carrying out the trip planning according to the user information and the interaction information, wherein the user information comprises user portraits, historical behavior data and scene perception data;
generating travel content and displaying the travel content according to the destination and the user information by using a large language model;
and under the condition that a confirmation instruction input based on the journey content is received, obtaining a journey planning task list according to the confirmation instruction, and displaying the journey planning task list according to a list display rule.
In a second aspect, an embodiment of the present application provides a trip planning apparatus based on a large language model, including:
the information acquisition module is used for receiving an input trip planning request, acquiring user information and interaction information associated with the trip planning request, and determining a destination for carrying out trip planning according to the user information and the interaction information, wherein the user information comprises user portraits, historical behavior data and scene perception data;
The journey planning module is used for generating journey content and displaying the journey content according to the destination and the user information by using a large language model;
and the journey confirmation module is used for obtaining a journey planning task list according to the confirmation instruction under the condition that the confirmation instruction input based on the journey content is received, and displaying the journey planning list according to a list display rule.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, where the processor implements the steps in the large language model-based trip planning method described in any one of the above when the computer program is executed.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps in the large language model-based trip planning method of any one of the above.
The embodiment of the application provides a journey planning method, device, electronic equipment and storage medium based on a large language model, wherein in the journey planning process, user information of a user who performs journey planning is firstly obtained, the obtained user information at least comprises user portraits, historical behavior data and scene perception data, meanwhile, interaction information with the user is also obtained, a destination for performing journey planning is determined according to the obtained user information and the interaction information, then the large language model is utilized for planning and recommending journey contents according to the destination and the user information, and finally a corresponding journey planning task list is generated under the condition that the journey is determined to be proper. The method and the device realize accurate planning of the journey according to the user portrait, the historical behavior data and the scene perception data in the journey planning process, can more accurately obtain the journey planning meeting the user requirements, and improve the accuracy and the rationality of the journey planning.
Drawings
FIG. 1 is a schematic flow chart of a journey planning method based on a large language model according to an embodiment of the application;
FIG. 2 is a flow chart of the steps provided in embodiments of the present application for determining a destination for a trip plan;
FIG. 3 is a flowchart illustrating the steps for determining a destination based on user information provided by an embodiment of the present application;
FIG. 4 is a schematic view of an interface for travel content presentation provided by an embodiment of the present application;
FIG. 5 is a block diagram illustrating a process for trip planning and execution of commands provided by an embodiment of the present application;
FIG. 6 is a block diagram illustrating a process for determining a destination according to an embodiment of the present application
FIG. 7 is a block diagram illustrating steps for performing trip alerting and performing detection provided by embodiments of the present application;
FIG. 8 is a schematic structural diagram of a trip planning device based on a large language model according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 10 is another schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below.
In the related art, when the trip planning is performed, the conventional trip planning mainly uses a manual arrangement mode, and relies on personal experience, knowledge and the like to perform matching and recommendation of trip content, so that the trip content may be wrong or inaccurate in matching, thereby affecting the actual trip experience, for example, the trip planning mode based on a predefined rule and a recommendation model can not accurately know the actual requirements of different users due to the limitation of the rule and the limitation of a model training sample, and further the recommendation of the trip is inaccurate.
In order to solve the technical problems in the related art, the embodiment of the present application provides a large language model-based trip planning method, please refer to fig. 1, fig. 1 is a schematic flow chart of the large language model-based trip planning method provided in the embodiment of the present application, and the method includes steps 101 to 103.
Step 101, receiving an input trip planning request, acquiring user information and interaction information related to the trip planning, and determining a destination for carrying out the trip planning according to the user information and the interaction information, wherein the user information comprises user portraits, historical behavior data and scene perception data.
In one embodiment, when planning a trip, a destination of the trip needs to be determined, and then corresponding trip planning is performed according to actual user requirements and the destination. Specifically, under the condition that the travel planning is determined, the processes such as the travel planning, the adjustment and the like are completed through man-machine interaction, in the interaction process, a travel planning request input by a user is received, then associated user information and interaction information are obtained, a destination for the travel planning is determined according to the obtained user information and interaction information, and in order to enable the travel planning to be more accurate and close to user requirements, the obtained user information at least comprises user portraits, historical behavior data and scene perception data.
The obtained user information is user information of equipment for interacting with the trip planning equipment or the system, such as a mobile phone user, the interaction information is data information generated in a user interaction process, the user portrait can be description of a user, such as gender, age, work function and the like, the historical behavior data can be historical data of a user using a terminal, such as an API of a three-party application service, and the scene perception data can be environmental information, such as a position, of the user.
It should be noted that, the terminal or device for performing the trip planning by the user may be a mobile device such as a mobile phone or a computer, and the corresponding trip planning system is configured in the terminal or device, and then the user completes the trip planning by the operation on the system in the process of interacting with the terminal or device. In order to more accurately complete the trip planning, the user information needs to be acquired correspondingly, so that the configured trip planning system needs to have necessary permission to access the sensing data (such as the current position, the current time, the current state and the like) provided by the system, the acquisition of the user portrait (such as the user consumption level, the consumption habit, the traffic habit, the eating habit and the like) data, the acquisition of system notification messages, short messages and the like, the acquisition of the information of the user booking, reservation and the like, and the access of the APIs of the three-party application services accessed by the system such as weather, searching, food, hotels and the like.
Further, after obtaining the user information and the interaction information, it is first required to determine a destination to which the user wants to reach, so as to perform planning of the trip, specifically referring to fig. 2, fig. 2 is a schematic flow chart of a step of determining a destination of the trip plan provided in an embodiment of the present application, where the step includes steps 201 to 203.
Step 201, receiving an input trip planning request, and acquiring user information and interaction information associated with the trip planning request;
step 202, carrying out semantic recognition on the interaction information to obtain semantic information corresponding to the interaction information;
and 203, determining a destination for trip planning according to the user information and the semantic information.
Specifically, when determining the destination of the trip plan, the determination is based on the user information and the interaction information, and in practical application, there may be a required destination or no required destination in the interaction information, so when determining the destination, firstly, semantic recognition is performed on the interaction information to obtain semantic information corresponding to the interaction information, and then, the destination of the trip plan is determined according to the user information and the semantic information.
For example, the semantic information corresponding to the interaction information may or may not include location information, and the manner of determining the destination is different in different cases, specifically, when the semantic information includes location information, the destination for performing trip planning may be determined, and when the semantic information does not include location information, recommendation of the destination based on the user information may be required, so as to determine the destination for performing trip planning.
For example, when the interactive information is "i want to travel to the marry", the destination that is desired at this time is "marry" can be determined by semantic recognition and analysis, and when the interactive information is "i want a travel course of three days and two nights", the destination is not determined based on the interactive information, that is, the destination is unknown, so further confirmation based on the user information will be required.
Accordingly, when determining a destination to conduct trip planning based on the user information and the semantic information, it includes: word segmentation processing is carried out on the semantic information, and whether the semantic information contains location information or not is determined; determining a destination in the obtained location information according to the semantic information under the condition that the semantic information contains the location information; and under the condition that the semantic information does not contain the place information, obtaining a destination set according to the user information, and determining a destination for trip planning in the destination set.
Specifically, after obtaining the user information and the semantic information, word segmentation is performed on the semantic information, and whether the semantic information contains location information is determined according to the word segmentation result, wherein the location information can be a location name, analysis is performed according to the semantic information when the location information is determined to be contained in the semantic information, whether the contained location information is a destination is determined, and recommendation processing of the destination is performed according to the user information when the location information is determined not to be contained in the semantic information.
For example, when the place information is determined to be included in the semantic information, the obtained place information cannot be directly taken as a destination because the place information is obtained through word segmentation, for example, the semantic information obtained through semantic recognition is "buying a ticket from martial arts to Shenzhen", the obtained place information is provided with two martial arts and Shenzhen through word segmentation, and the destination can be intuitively determined to be Shenzhen according to the semantic information, and at the moment, the judgment is performed by combining the actual semantic information when the destination is determined.
When determining that the semantic information does not include the location information, determining the destination according to the user information acquired in advance, specifically, referring to fig. 3, fig. 3 is a flowchart illustrating steps of determining the destination based on the user information, where the steps include steps 301 to 303.
Step 301, performing behavior analysis according to user information, and determining a destination candidate set for trip planning;
step 302, generating location selection information according to a destination candidate set;
step 303, receiving a selection instruction input in response to the location selection information, and determining a destination for trip planning according to the selection instruction.
Specifically, under the condition that the semantic information does not contain the place information, analysis processing is carried out on the user information, a destination candidate set for carrying out journey planning is determined, then place selection information is generated according to the obtained destination candidate set, and further after a selection instruction responding to the place selection information is received, a destination for carrying out journey planning is determined according to the selection instruction.
The obtained user information comprises user portraits, historical behavior data and scene perception data, and reasonable requirements of the user are determined when the user information is analyzed, so that possible destinations of the user are determined according to the reasonable requirements. For example, when the interactive information is "i want a three-day two-night travel itinerary", it is indicated that the user wants to travel, at this time, operation data of the user on each application program, such as search information and attack information, can be obtained, and location screening processing can be performed, and at the same time, location screening can be performed again according to the user portrait, and a destination candidate set can be obtained through continuous analysis and screening, so that the user can select.
For example, the number of destinations obtained from the search record and the attack record of the user is 10, then when screening is performed according to the user portrait, the 10 obtained destinations obtained in consideration of the consumption level, the consumption habit, the eating habit and the like of the user can be notified to screen again, 3 destinations are obtained, and at this time, 3 destinations can be used as a destination candidate set, so that the user can select to determine the destination.
Further, when the semantic information is subjected to word segmentation to determine whether location information is included, there is a special case that the semantic information does not include location information, but a destination can be determined based on the semantic information and the acquisition of an API of the three-party application service, for example, when the semantic information is "buying a ticket to go home", the semantic information is determined to be not included in analysis, but the destination can be determined to be "home" by semantic analysis, and only because "home" is not a place name, the judgment is inaccurate, when the situation occurs, the destination can be determined by acquiring information in the three-party application service, for example, the address of the set "home" can be acquired in the navigation application, and then the destination corresponding to the current destination can be determined.
And 102, generating travel content and displaying the travel content according to the destination and the user information by using the large language model.
In one embodiment, after determining the destination at which to conduct trip planning, trip content is generated from the destination and user information using a large language model, and the generated trip content is presented such that trip confirmation is conducted through interaction with the user.
The generated travel content at least comprises travel time, travel location and travel description. For example, one trip content may be: 8 points of high-speed rail in the morning, wuhan to Shenzhen.
In one embodiment, after the travel content is generated, the user may view, edit, and reprogram the travel content, so that the method further includes, after the travel content is generated: and displaying the travel content on the associated terminal display interface based on the travel time sequence, and sending a travel content confirmation instruction.
That is, after the travel content is generated, the user may view the travel content, and in order to facilitate viewing and subsequent processing, the travel content may be displayed on the associated terminal display interface according to the time sequence of the travel, and a travel content confirmation instruction may be sent.
For example, after obtaining the travel content, the user is required to determine whether the travel is feasible, so the travel content can be displayed on a display interface, such as a mobile phone, for the user to view and confirm the travel, and in particular, when the travel content is displayed, reference may be made to fig. 4, and fig. 4 is a schematic interface diagram of travel content display provided in the embodiments of the present application.
When the travel content is displayed, the travel content is displayed on the interface in a travel time sequence manner, as shown in fig. 4 (a), and a certain time sequence relationship exists between the travel. And when the travel is determined to be feasible, the process can be finished by clicking a confirmed virtual key on a real interface.
Further, when the travel content is displayed, the travel content can be checked, edited, modified and the like, which specifically comprises: under the condition that a travel checking instruction is received, determining a first travel for checking, and displaying sub-travel contained in the first travel; and under the condition that the journey editing instruction is received, receiving input editing information and/or voice information, and updating journey content according to the editing information and/or voice information.
For example, when viewing the travel content, the user may click on the first travel required to be viewed, and at this time, the sub-travel included in the first travel is displayed, as shown in fig. 4 (b). As shown in the figure, when viewing, by clicking on the travel item 2/row Cheng Xiang 3, the information contained in the travel item 2/travel item 3 can be viewed, for example, when the travel item 2 is an accommodation, the displayed sub-travel item is selectable accommodation content, specific accommodation information can be determined by selection, and similarly, when the travel item 3 is a food, the displayed sub-travel item is selectable food content, and specific food is determined by selection.
In addition, the sub-journey included in each journey can be determined when the journey planning is carried out, then the planned content, such as resident hotels, clapping scenic spots and the like, can be directly displayed when the journey planning is carried out, and the planned journey can be modified and adjusted.
For another example, in the case where a trip edit instruction is received, corresponding edit information and/or voice information may be input through interaction, and then trip content is interacted through recognition of the edit information and/or voice information, as shown in fig. 4 (c). At this time, when the processes such as editing and modifying the journey are performed, the whole journey may be adjusted, for example, the journey planning may be performed again, or a certain journey item may be adjusted, and when the adjustment is performed, the adjustment may be completed through specific interaction.
And step 103, under the condition that a confirmation instruction input based on the travel content is received, obtaining a travel planning task list according to the confirmation instruction, and displaying the travel planning task list according to a list display rule.
In one embodiment, in the event that a confirmation instruction based on the itinerary content input is received through interaction, a user's current selection instruction is determined to determine an itinerary list, and the itinerary list is presented according to a corresponding list presentation rule.
Specifically, after the travel content is displayed, the user can adjust the travel content according to the requirement, and further after the adjustment is determined, the user clicks a confirmation button on the interface to output and obtain a travel planning task list, wherein the travel planning task list is generated based on the travel content, and at the moment, the travel planning task list cannot be modified.
Further, when the trip planning task list is obtained, in order that the trip can be normally executed, it is necessary to ensure that each trip in the trip planning task list has no trip conflict, so when the trip planning task list is obtained, the method further includes: performing conflict analysis on the travel content to determine whether travel conflict exists in the travel content; and when the travel conflict is determined to exist, marking the travel with the travel conflict, and carrying out modification feedback on the travel with the travel conflict.
Specifically, when it is determined that the route planning task list can be generated, analysis of route conflict is needed to be performed on the determined route content, whether problems exist in the routes or whether conflict exists between the routes is determined, and therefore the executing reasonability of the routes is guaranteed. And determining whether the travel conflict exists between the travel contents by carrying out conflict analysis on the determined difficult content, and marking the travel with the conflict and giving reasonable travel modification opinion when the travel conflict exists.
In addition, when executing the travel, since there is a certain time sequence relationship between the travel, there is a certain sequence of the travel execution, the method includes: selecting a first procedure from a procedure planning task list according to a time sequence, and acquiring current time information and current position information; determining whether to carry out journey reminding according to the current time information, the current position information and journey time and journey place contained in the first journey; and under the condition that the travel reminding is determined, corresponding reminding information is generated for feedback.
In the course of executing the journey, the first journey is selected from the planned task list after the journey is measured, in general, the first journey is the first journey, in order to ensure that the user can complete the journey on time, corresponding reminding can be performed on the user according to actual conditions, the first journey is taken as an example, before reminding, current time information and current position information, namely, perception data, are obtained, then whether to carry out journey reminding is determined according to the current time information, the current position information and journey time and journey place contained in the first journey, and further corresponding reminding information is sent out under the condition that the reminding is determined, wherein the reminding information can be to-be-done information on the mobile phone.
Further, during execution of the journey, a timely record may be made of the completed journey for subsequent viewing, specifically, when the journey is recorded, the method includes: acquiring stroke execution data when executing the second stroke under the condition that the second stroke is detected to be completed; correlating the travel execution data with the second travel generation, and generating a travel record corresponding to the second travel; and under the condition that a sharing instruction for the second journey is received, sharing information is generated according to the journey record.
Illustratively, during the recording process, the user can be automatically assisted in recording by position, time, current journey items and the like, associating photos, videos and the like taken by the user during the journey, and manually written word records by the user, such as mood records, diaries, evaluations and the like; the system can automatically help the user to associate the related content with the corresponding travel item; the user may also manually make content associations or recordings.
And when the travel sharing is carried out, partial or all travel records can be exported and shared, the exported travel records comprise specific travel contents, time schedule, photos, videos, text records of users and other complete travel records, the exporting mode can be exported in a graphic form, and the graphic records can be subjected to proper editing, color rendering, adjustment and other optimization processing through LLM.
Further, referring to fig. 5, fig. 5 is a schematic block diagram of a process for planning a trip and executing a command according to an embodiment of the present application.
As can be seen from fig. 5, when planning and executing the journey, the method mainly comprises the following steps:
and step 1, planning and making a preliminary journey.
Specifically, when the preliminary trip planning is performed, the destination needs to be determined first, and then the preliminary trip planning generation is completed according to the determined destination and related information.
The destination may be entered directly by the user when determining the destination, or may be determined by recommendation when, and in the case where the destination is determined, the preliminary trip planning generation will be performed directly. And when the destination is not clear, reference may be made to fig. 6, where fig. 6 is a schematic block diagram of a procedure for determining the destination according to an embodiment of the present application.
When determining the destination, generating a three-party service query request by using LLM according to a user request, portrait data, scene perception data, user history data and the like of the user, wherein the query request comprises a requested three-party service API name, corresponding parameters and the like. In order to take a user request as 'please help me recommend a three-day two-night travel journey', three-party service APIs are utilized to obtain three-party service providing related travel destination recommendation data (structured/semi-structured/unstructured data can be obtained), then the three-party service APIs are called, corresponding return contents are analyzed and obtained to be fed back to a planning engine, and then the planning engine utilizes LLM to conduct personalized destination recommendation according to user requirements, user portrait data, scene perception data, user history data and return contents of the three-party service APIs, wherein personalization is to fully consider requirements, preferences, consumption habits, consumption levels and the like of users, recommendation meeting user expectations is given, and meanwhile, reference information sources can be attached to recommendation results so that the users can check and verify conveniently.
It should be noted that, after the user selects a suitable destination, the user may perform a next trip planning, and if the recommended destination is not satisfied, more demand descriptions may be added by a dialogue manner, so as to obtain a destination meeting the demand of the user, and the destination may be plural.
Further, after determining the destination, a corresponding preliminary trip plan will be generated based on the destination. Specifically, when performing preliminary trip planning, the planning engine generates a three-party service query request according to the requirements of a user, the portrait data of the user, scene perception data, user history data and the like by using the LLM, the query request comprises the name of the requested three-party service API, corresponding parameters and the like, and then performs personalized trip planning recommendation according to the requirements of the user, the portrait data of the user, the scene perception data, the user history data and the returned content of the API of the three-party service by using the LLM.
In the case of generating the initial trip plan, the same manner as the determination of the destination is adopted, except that the destination of the output is determined when the destination is determined, and the initial trip plan after the planning is outputted when the trip plan is performed.
And 2, editing and confirming the journey planning.
After the planning is completed to obtain an initial trip plan, the trip may be edited and validated, and in particular, the obtained initial trip plan may be presented on a display interface in a manner as shown in fig. 4. The whole journey planning can be displayed and interacted with the user in a time line mode, so that the user can more intuitively know the content of the whole journey.
For the displayed information, the user can edit, add, delete, adjust the sequence and the like of the travel items, and for unsatisfactory travel planning, the user can also reset and regenerate through a top menu, wherein the top menu comprises functions such as travel confirmation, travel perfection, travel conflict analysis, travel reminding item generation, one-key reset and the like, and operations such as regeneration and withdrawal.
Wherein, the editing of the journey by the user can be realized in two ways: editing is performed by means of a dialog using a planning engine and manual editing by a user.
For example, when the journey problem analysis is performed, the planning engine utilizes the LLM to perform the problem analysis on the existing journey planning content in combination with the user portrait, scene perception and other data, including but not limited to journey conflict items, journey loose degree, journey expense, journey time consumption, journey risk and the like, and gives corresponding modification comments.
For another example, when the trip reminding is performed, the planning engine generates information such as time, content, duration and the like of the trip reminding for the existing trip item content by using the LLM; for example, 24 hours before the user goes out, reminding the user to prepare the required items for the relevant travel; reminding the user of the time at which the next item of programming starts, matters that need to be prepared in advance, and the like.
And 3, stroke reminding and execution detection.
For the executing journey, the journey plan may be reminded and the executing state detected through the flow shown in fig. 7.
Specifically, when carrying out newcastle reminding and executing detection, the method comprises the following steps:
(1) The next program item content is acquired in sequence.
(2) Reminding the scheduled content at the scheduled time according to the travel item content, wherein the reminding content comprises, but is not limited to, the recommended content, future weather, road conditions, scheduled time and the like, meanwhile, the reminding content can be presented to a user in various modes such as a notification message, a negative one-screen card, a desktop card, a pop-up message and the like, different reminding modes, duration and the like can be customized according to the specific reminding content, clicking the reminding content can jump to a travel planning detail page to check detailed information, clicking the recommended content can jump to a three-party service to perform further operation;
(3) The system utilizes the perception data to detect and remind, such as time, position, state and the like, to judge and monitor the journey state, for example, based on the position and time information, whether the user drives to an airport/station on time or not is judged;
(4) For the travel items which cannot be monitored through the perception data, such as article preparation, material purchase and the like, the subsequent travel items which can be monitored can be indirectly monitored, and a user can confirm the travel items manually;
(5) And marking the current travel progress. The completed travel items may be marked in a timeline list, and the progress of the current travel may be identified in the timeline in the manner of a progress bar;
(6) If the current journey execution abnormality is monitored, if a user does not arrive at a station/airport or the like in a preset time and cannot catch up with a preset number of cars or flights, or does not catch up to the next destination in the preset time and cannot normally execute the next journey item, a prompt is sent to the user, and reasonable modification advice is given;
(7) If the user confirms that the journey needs to be modified, the journey planning content is unlocked, the journey editing and confirmation are carried out in step 2, and the completed journey item cannot be edited.
In addition, the user may perform a trip cancel operation during the trip execution.
And 4, stroke recording.
And 5, stroke sharing.
In summary, the application discloses a journey planning method based on a large language model, in the process of carrying out journey planning, firstly, user information of a user carrying out journey planning is obtained, the obtained user information at least comprises user portraits, historical behavior data and scene perception data, meanwhile, interaction information with the user is obtained, so that a destination for carrying out journey planning is determined according to the obtained user information and the interaction information, then, the large language model is utilized for planning and recommending journey contents according to the destination and the user information, and finally, a corresponding journey planning task list is generated under the condition that the journey is determined to be proper. The method and the device realize accurate planning of the journey according to the user portrait, the historical behavior data and the scene perception data in the journey planning process, can more accurately obtain the journey planning meeting the user requirements, and improve the accuracy and the rationality of the journey planning.
According to the method described in the above embodiments, the present embodiment will be further described from the perspective of a large language model-based trip planning apparatus, which may be implemented as a separate entity, or may be implemented as an integrated electronic device, such as a terminal, which may include a mobile phone, a tablet computer, or the like.
Referring to fig. 8, fig. 8 is a schematic structural diagram of a large language model-based trip planning apparatus according to an embodiment of the present application, and as shown in fig. 8, a large language model-based trip planning apparatus 800 according to an embodiment of the present application includes:
the information acquisition module 801 is configured to receive an input trip planning request, acquire user information and interaction information associated with the trip planning request, and determine a destination for performing trip planning according to the user information and the interaction information, where the user information includes a user portrait, historical behavior data, and scene perception data;
the trip planning module 802 is configured to generate and display trip content according to destination and user information by using a large language model;
and the trip confirmation module 803 is configured to obtain a trip planning task list according to the confirmation instruction and display the trip planning list according to the list display rule when receiving the confirmation instruction input based on the trip content.
In an embodiment, the information obtaining module 801 is further configured to:
receiving an input journey planning request, and acquiring user information and interaction information associated with the journey planning request;
carrying out semantic recognition on the interaction information to obtain semantic information corresponding to the interaction information;
And determining a destination for trip planning according to the user information and the semantic information.
In an embodiment, the information obtaining module 801 is further configured to:
word segmentation processing is carried out on the semantic information, and whether the semantic information contains location information or not is determined;
determining a destination in the obtained location information according to the semantic information under the condition that the semantic information contains the location information;
and under the condition that the semantic information does not contain the place information, obtaining a destination set according to the user information, and determining a destination for trip planning in the destination set.
In an embodiment, the information obtaining module 801 is further configured to:
performing behavior analysis according to the user information, and determining a destination candidate set for trip planning;
generating location selection information from the destination candidate set;
and receiving a selection instruction input in response to the location selection information, and determining a destination for trip planning according to the selection instruction.
In one embodiment, the large language model based trip planning apparatus 800 further includes a trip confirmation module for:
and displaying the travel content on the associated terminal display interface based on the travel time sequence, and sending a travel content confirmation instruction.
In one embodiment, the large language model based trip planning apparatus 800 further includes a trip analysis module for:
performing conflict analysis on the travel content to determine whether travel conflict exists in the travel content;
and when the travel conflict is determined to exist, marking the travel with the travel conflict, and carrying out modification feedback on the travel with the travel conflict.
In one embodiment, the large language model based trip planning apparatus 800 further includes a trip view module for:
under the condition that a travel checking instruction is received, determining a first travel for checking, and displaying sub-travel contained in the first travel;
and under the condition that the journey editing instruction is received, receiving input editing information and/or voice information, and updating journey content according to the editing information and/or voice information.
In one embodiment, the trip planning apparatus 800 based on the large language model further includes a trip alert module for:
selecting a first procedure from a procedure planning task list according to a time sequence, and acquiring current time information and current position information;
determining whether to carry out journey reminding according to the current time information, the current position information and journey time and journey place contained in the first journey;
And under the condition that the travel reminding is determined, corresponding reminding information is generated for feedback.
In one embodiment, the large language model based trip planning apparatus 800 further includes a trip recording module for:
acquiring stroke execution data when executing the second stroke under the condition that the second stroke is detected to be completed;
correlating the travel execution data with the second travel generation, and generating a travel record corresponding to the second travel;
and under the condition that a sharing instruction for the second journey is received, sharing information is generated according to the journey record.
In one embodiment, the travel content includes at least travel time, travel location, and travel description.
In addition, referring to fig. 9, fig. 9 is a schematic structural diagram of an electronic device provided in an embodiment of the present application, where the electronic device may be a mobile terminal, such as a smart phone, a tablet computer, or the like. As shown in fig. 9, the electronic device 900 includes a processor 901 and a memory 902. The processor 901 is electrically connected to the memory 902.
Processor 901 is a control center of electronic device 900 that connects various portions of the overall electronic device using various interfaces and lines, and performs various functions of electronic device 900 and processes data by running or loading applications stored in memory 902, and invoking data stored in memory 902, thereby performing overall monitoring of electronic device 900.
In this embodiment, the processor 901 in the electronic device 900 loads instructions corresponding to the processes of one or more application programs into the memory 902 according to the following steps, and the processor 901 runs the application program stored in the memory 902, so as to implement any step of the trip planning method based on the large language model provided in the foregoing embodiment.
The electronic device 900 may implement the steps in any embodiment of the large language model-based trip planning method provided in the embodiments of the present application, so that the beneficial effects that any large language model-based trip planning method provided in the embodiments of the present application can be implemented, which are detailed in the previous embodiments and are not described herein.
Referring to fig. 10, fig. 10 is another schematic structural diagram of an electronic device provided in an embodiment of the present application, and fig. 10 is a specific structural block diagram of the electronic device provided in the embodiment of the present application, where the electronic device may be used to implement the trip planning method based on a large language model provided in the embodiment described above. The electronic device 1000 may be a mobile terminal such as a smart phone or a notebook computer.
The RF circuit 1010 is configured to receive and transmit electromagnetic waves, and to perform mutual conversion between the electromagnetic waves and the electrical signals, thereby communicating with a communication network or other devices. RF circuitry 1010 may include various existing circuit elements for performing these functions, such as an antenna, a radio frequency transceiver, a digital signal processor, an encryption/decryption chip, a Subscriber Identity Module (SIM) card, memory, and so forth. The RF circuitry 1010 may communicate with various networks such as the internet, intranets, wireless networks, or other devices via wireless networks. The wireless network may include a cellular telephone network, a wireless local area network, or a metropolitan area network. The wireless network may use various communication standards, protocols, and technologies including, but not limited to, global system for mobile communications (Global System for Mobile Communication, GSM), enhanced mobile communications (Enhanced Data GSM Environment, EDGE), wideband Code Division multiple access (Wideband Code Division MultipleAccess, WCDMA), code Division multiple access (Code DivisionAccess, CDMA), time Division multiple access (Time Division MultipleAccess, TDMA), wireless fidelity (Wireless Fidelity, wi-Fi) (e.g., institute of electrical and electronics engineers (IEEE 802.11a,IEEE 802.11b,IEEE802.11g) and/or IEEE802.11 n), internet telephony (Voice over Internet Protocol, voIP), worldwide interoperability for microwave access (Worldwide Interoperability for Microwave Access, wi-Max), other protocols for mail, instant messaging, and short messaging, and any other suitable communication protocols, even those not currently developed.
The memory 1020 may be used to store software programs and modules, such as program instructions/modules corresponding to the large language model-based trip planning method in the above embodiments, and the processor 1080 may execute various functional applications and the large language model-based trip planning method by running the software programs and modules stored in the memory 1020.
Memory 1020 may include high-speed random access memory, but may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory. In some examples, memory 1020 may further include memory located remotely from processor 1080, which may be connected to electronic device 1000 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input unit 1030 may be used for receiving input numeric or character information and generating keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. In particular, the input unit 1030 may include a touch-sensitive surface 1031 and other input devices 1032. The touch-sensitive surface 1031, also referred to as a touch display screen or touch pad, may collect touch operations thereon or thereabout by a user (e.g., operations of the user on the touch-sensitive surface 1031 or thereabout using any suitable object or accessory such as a finger, stylus, etc.), and actuate the corresponding connection device according to a pre-set program. Alternatively, the touch sensitive surface 1031 may comprise two parts, a touch detection device and a touch controller. The touch detection device detects the touch azimuth of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device and converts it into touch point coordinates, which are then sent to the processor 1080 and can receive commands from the processor 1080 and execute them. In addition, the touch sensitive surface 1031 may be implemented in a variety of types, such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch-sensitive surface 1031, the input unit 1030 may include other input devices 1032. In particular, other input devices 1032 may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a track ball, a mouse, a joystick, etc.
The display unit 1040 may be used to display information input by a user or information provided to a user, and various graphical user interfaces of the electronic device 1000, which may be composed of graphics, text, icons, video, and any combination thereof. The display unit 1040 may include a display panel 1041, and alternatively, the display panel 1041 may be configured in the form of an LCD (Liquid Crystal Display ), an OLED (Organic Light-Emitting Diode), or the like. Further, the touch sensitive surface 1031 can overlay the display panel 1041, and upon detection of a touch operation thereon or thereabout by the touch sensitive surface 1031, is communicated to the processor 1080 to determine a type of touch event, and the processor 1080 then provides a corresponding visual output on the display panel 1041 based on the type of touch event. Although in the figures the touch sensitive surface 1031 and the display panel 1041 are implemented as two separate components, in some embodiments the touch sensitive surface 1031 may be integrated with the display panel 1041 to implement the input and output functions.
The electronic device 1000 can also include at least one sensor 1050, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 1041 according to the brightness of ambient light, and the proximity sensor may generate an interruption when the flip cover is closed or closed. As one of the motion sensors, the gravity acceleration sensor can detect the acceleration in all directions (generally three axes), and can detect the gravity and the direction when the mobile phone is stationary, and can be used for applications of recognizing the gesture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer gesture calibration), vibration recognition related functions (such as pedometer and knocking), and the like; other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc. that may also be configured with the electronic device 1000 are not described in detail herein.
Audio circuitry 1060, a speaker 1061, and a microphone 1062 may provide an audio interface between a user and the electronic device 1000. Audio circuit 1060 may transmit the received electrical signal after audio data conversion to speaker 1061 for conversion by speaker 1061 into an audio signal output; on the other hand, microphone 1062 converts the collected sound signals into electrical signals, which are received by audio circuit 1060 and converted into audio data, which are processed by audio data output processor 1080 for transmission to, for example, another terminal via RF circuit 1010 or for output to memory 1020 for further processing. Audio circuitry 1060 may also include an ear bud jack to provide communication of the peripheral headphones with the electronic device 1000.
The electronic device 1000, via a transmission module 1070 (e.g., wi-Fi module), may facilitate user reception of requests, transmission of information, etc., that provides wireless broadband internet access to the user. Although a transmission module 1070 is shown, it is understood that it is not an essential component of the electronic device 1000 and can be omitted entirely as desired within the scope of not changing the essence of the invention.
Processor 1080 is a control center of electronic device 1000 and utilizes various interfaces and lines to connect the various parts of the overall handset, perform various functions of electronic device 1000 and process data by running or executing software programs and/or modules stored in memory 1020, and invoking data stored in memory 1020, thereby performing overall monitoring of the electronic device. Optionally, processor 1080 may include one or more processing cores; in some embodiments, processor 1080 may integrate an application processor primarily handling operating systems, user interfaces, applications, and the like, with a modem processor primarily handling wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 1080.
The electronic device 1000 also includes a power source 1090 (e.g., a battery) that provides power to the various components and, in some embodiments, is logically coupled to the processor 1080 via a power management system to manage charging, discharging, and power consumption. The power source 1090 may also include one or more of any of a direct current or alternating current power source, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.
Although not shown, the electronic device 1000 further includes a camera (such as a front camera, a rear camera), a bluetooth module, etc., and will not be described herein. In particular, in this embodiment, the display unit of the electronic device is a touch screen display, and the mobile terminal further includes a memory, and one or more programs, where the one or more programs are stored in the memory, and configured to be executed by the one or more processors, where the one or more programs implement any step of the large language model-based trip planning method provided in the foregoing embodiment.
In the implementation, each module may be implemented as an independent entity, or may be combined arbitrarily, and implemented as the same entity or several entities, and the implementation of each module may be referred to the foregoing method embodiment, which is not described herein again.
Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor. To this end, the present embodiment provides a storage medium having stored therein a plurality of instructions that when executed by a processor are capable of implementing any of the steps of the large language model based trip planning method provided by the above embodiment.
Wherein the storage medium may include: read Only Memory (ROM), random access Memory (RAM, randomAccess Memory), magnetic disk or optical disk, and the like.
Because the instructions stored in the storage medium may perform the steps in any embodiment of the large language model-based trip planning method provided in the embodiments of the present application, the beneficial effects that any large language model-based trip planning method provided in the embodiments of the present application may be achieved, which are detailed in the previous embodiments and are not described herein.
The foregoing describes in detail a trip planning method, apparatus, electronic device and storage medium based on a large language model provided in the embodiments of the present application, and specific examples are applied to illustrate the principles and embodiments of the present application, where the foregoing description of the embodiments is only for helping to understand the method and core ideas of the present application; meanwhile, as those skilled in the art will vary in the specific embodiments and application scope according to the ideas of the present application, the contents of the present specification should not be construed as limiting the present application in summary. Moreover, it will be apparent to those skilled in the art that various modifications and variations can be made without departing from the principles of the present application, and such modifications and variations are considered to be within the scope of the present application.
Claims (13)
1. A large language model-based trip planning method, comprising:
receiving an input trip planning request, acquiring user information and interaction information associated with the trip planning, and determining a destination for carrying out the trip planning according to the user information and the interaction information, wherein the user information comprises user portraits, historical behavior data and scene perception data;
generating travel content and displaying the travel content according to the destination and the user information by using a large language model;
and under the condition that a confirmation instruction input based on the journey content is received, obtaining a journey planning task list according to the confirmation instruction, and displaying the journey planning task list according to a list display rule.
2. The method of claim 1, wherein the receiving the input trip plan request, obtaining user information and interaction information associated with the trip plan, and determining a destination for the trip plan based on the user information and the interaction information, comprises:
receiving an input journey planning request, and acquiring user information and interaction information associated with the journey planning request;
Carrying out semantic recognition on the interaction information to obtain semantic information corresponding to the interaction information;
and determining a destination for carrying out journey planning according to the user information and the semantic information.
3. The method of claim 2, wherein determining a destination for trip planning based on the user information and the semantic information comprises:
word segmentation processing is carried out on the semantic information, and whether the semantic information contains location information or not is determined;
determining a destination in the obtained location information according to the semantic information under the condition that the semantic information contains the location information;
and under the condition that the semantic information does not contain the place information, obtaining a destination set according to the user information, and determining a destination for planning the journey in the destination set.
4. The method of claim 3, wherein the obtaining a set of destinations from the user information and determining a destination for trip planning in the set of destinations comprises:
performing behavior analysis according to the user information, and determining a destination candidate set for trip planning;
Generating location selection information from the destination candidate set;
and receiving a selection instruction input in response to the place selection information, and determining a destination for planning a journey according to the selection instruction.
5. The method of claim 1, wherein the method further comprises:
and displaying the travel content on the associated terminal display interface based on the travel time sequence, and sending a travel content confirmation instruction.
6. The method of claim 1, wherein the method further comprises:
performing conflict analysis on the travel content to determine whether travel conflict exists in the travel content;
and when the travel conflict is determined to exist, marking the travel with the travel conflict, and carrying out modification feedback on the travel with the travel conflict.
7. The method of claim 1, wherein the method further comprises:
under the condition that a travel viewing instruction is received, determining a first travel for viewing, and displaying sub-travel contained in the first travel;
and under the condition that the journey editing instruction is received, receiving input editing information and/or voice information, and updating the journey content according to the editing information and/or the voice information.
8. The method of claim 1, wherein the exposing the trip planning task list according to list-exposing rules comprises:
selecting a first journey in the journey planning task list according to a time sequence, and acquiring current time information and current position information;
determining whether to carry out journey reminding according to the current time information, the current position information and journey time and journey place contained in the first journey;
and under the condition that the travel reminding is determined, corresponding reminding information is generated for feedback.
9. The method of claim 1, wherein the method further comprises:
acquiring stroke execution data when executing a second stroke under the condition that the second stroke is detected to be completed;
correlating the travel execution data with the second travel generation and generating a travel record corresponding to the second travel;
and under the condition that a sharing instruction for the second journey is received, sharing information is generated according to the journey record.
10. The method of claim 1, wherein the travel content includes at least travel time, travel location, and travel description.
11. A large language model-based trip planning apparatus, comprising:
the information acquisition module is used for receiving an input trip planning request, acquiring user information and interaction information associated with the trip planning request, and determining a destination for carrying out trip planning according to the user information and the interaction information, wherein the user information comprises user portraits, historical behavior data and scene perception data;
the journey planning module is used for generating journey content and displaying the journey content according to the destination and the user information by using a large language model;
and the journey confirmation module is used for obtaining a journey planning task list according to the confirmation instruction under the condition that the confirmation instruction input based on the journey content is received, and displaying the journey planning list according to a list display rule.
12. An electronic device comprising a processor, a memory and a computer program stored in the memory and executable on the processor, the processor implementing the steps in the method according to any one of claims 1 to 10 when the computer program is executed.
13. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the steps in the method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311555179.2A CN117556155A (en) | 2023-11-20 | 2023-11-20 | Stroke planning method, device, equipment and storage medium based on large language model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311555179.2A CN117556155A (en) | 2023-11-20 | 2023-11-20 | Stroke planning method, device, equipment and storage medium based on large language model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117556155A true CN117556155A (en) | 2024-02-13 |
Family
ID=89820165
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311555179.2A Pending CN117556155A (en) | 2023-11-20 | 2023-11-20 | Stroke planning method, device, equipment and storage medium based on large language model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117556155A (en) |
-
2023
- 2023-11-20 CN CN202311555179.2A patent/CN117556155A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Emmanouilidis et al. | Mobile guides: Taxonomy of architectures, context awareness, technologies and applications | |
| US10890451B2 (en) | Place of interest recommendation | |
| US9638528B2 (en) | Method and apparatus for displaying geographic location | |
| US11537450B2 (en) | Method, apparatus, and mobile terminal for associating notification messages | |
| CN114584650B (en) | Method for pushing notification, electronic device and storage medium | |
| US20180268460A1 (en) | Method and apparatus for information recommendation | |
| EP2987164B1 (en) | Virtual assistant focused user interfaces | |
| KR101569470B1 (en) | Presenting information for a current location or time | |
| US20170243465A1 (en) | Contextual notification engine | |
| CN107302625B (en) | Method for managing events and terminal equipment thereof | |
| EP3627806A1 (en) | Method for generating user portrait, and terminal | |
| CN107391768B (en) | Webpage data processing method, device and equipment and computer readable storage medium | |
| CN102982440A (en) | Gathering and presenting task | |
| CN109074392A (en) | The resource manager of Contextually aware | |
| US20140025746A1 (en) | Apparatus and method for managing user information | |
| US10965888B1 (en) | Subtitle presentation based on volume control | |
| CN108958634A (en) | Express delivery information acquisition method, device, mobile terminal and storage medium | |
| JP7167131B2 (en) | Natural Language Processing and Analysis in Conversational Scheduling Assistant Computing System | |
| CN108205568A (en) | Method and device based on label selection data | |
| JP2017521739A (en) | Personal intelligence platform | |
| CN105229638A (en) | As the library manager of the robotization of the contributor of the collection to content | |
| CN107368998A (en) | Agenda managing method and Related product | |
| US11237706B2 (en) | Information processing method and terminal | |
| CN117650829A (en) | Communication system, method and terminal equipment | |
| CN117556155A (en) | Stroke planning method, device, equipment and storage medium based on large language model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |