File travel plan generation method and device, equipment, storage medium and program product

Abstract

The invention relates to the technical field of artificial intelligence, and particularly provides a text travel plan generation method and device, equipment, a storage medium and a program product, and the method comprises the steps: obtaining keywords related to a travel scene and daily behavior attribute parameters of the keywords based on collected daily behavior data representing habits and interests of a user; calculating weights of the keywords based on the daily behavior attribute parameters; reasoning the keywords and the weights by adopting a pre-trained large language model to obtain a plurality of travel plan draft plans; and obtaining the travel plan of the user from the plurality of travel plan draft plans. By collecting the daily behavior data of the user, places or scenic spots which the user may be interested in can be obtained, a text travel plan draft is made for the user, when the user has a travel thought but does not determine a travel place, the places which the user is interested in can be selected from the text travel plan draft, a detailed text travel plan is generated, planning by the user is not needed, and the user experience is improved. And the tour experience feeling of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, equipment, storage medium and program product for generating a cultural tourism plan. Background Art

[0002] In the prior art, cultural and tourism plans mostly rely on manual processing, that is, users search for target tourist cities, attractions, etc. and formulate corresponding travel plans. However, most users can only search for popular attractions in the target tourist cities on the Internet. These popular attractions are not all attractions that users are interested in, and relatively niche attractions that users may be interested in may not be searchable. Therefore, manually formulated travel plans bring users a poor travel experience, low efficiency, and long time consumption. In addition, if the user only has the idea or demand of traveling, but has not yet determined the target tourist city or is not familiar with the target tourist city, it is also difficult to formulate a suitable cultural and tourism plan through manual processing. Summary of the invention

[0003] The present application is proposed in view of the above-mentioned problems, and the present application provides a method, device, equipment, storage medium and program product for generating a cultural tourism plan.

[0004] According to one aspect of the present application, a method for generating a cultural tourism plan is provided, comprising:

[0005] Based on the collected daily behavior data representing the user's habits and interests, obtain keywords related to the travel scene and daily behavior attribute parameters of the keywords, wherein the daily behavior attribute parameters are used to represent the importance of the keywords;

[0006] Calculating the weight of the keyword based on the daily behavior attribute parameters;

[0007] A pre-trained large language model is used to infer the keywords and the weights to obtain multiple draft cultural tourism plans;

[0008] Obtain the cultural travel plan of the user from the multiple cultural travel plan drafts.

[0009] In addition, the method for generating a cultural tourism plan according to one aspect of the present application further includes: obtaining keywords related to tourism scenarios based on the collected daily behavior data representing user habits and interests, including:

[0010] Extracting primary keywords related to tourism scenarios from the daily behavior data;

[0011] Using the preset large language model, generating secondary keywords related to the tourism scene represented by the primary keywords, and generating tertiary keywords related to the tourism scene represented by the secondary keywords;

[0012] Based on the primary keyword, the secondary keyword and the tertiary keyword, the keyword is obtained.

[0013] In addition, the method for generating a cultural tourism plan according to one aspect of the present application further includes: calculating the weight of the keyword based on the daily behavior attribute parameters, including:

[0014] Obtaining the number of keywords included in the daily behavior attribute parameter, where the number of keywords is the number of times the keyword appears in the keyword level to which it belongs;

[0015] Calculate the product of the keyword frequency and the level weight corresponding to the keyword level to obtain a first weight;

[0016] The sum of the first weights is used as the weight of the keyword.

[0017] In addition, the method for generating a cultural tourism plan according to one aspect of the present application further includes: calculating the weight of the keyword based on the daily behavior attribute parameters, including:

[0018] Based on the keyword acquisition time included in the daily behavior attribute parameter, acquiring the time interval to which the keyword belongs;

[0019] Obtaining the number of times the keyword appears in the time interval to which it belongs, and calculating the product of the number and the time weight corresponding to the time interval to obtain a second weight;

[0020] The sum of the second weights is used as the weight of the keyword.

[0021] In addition, the method for generating a cultural tourism plan according to one aspect of the present application further includes: calculating the weight of the keyword based on the daily behavior attribute parameters, including:

[0022] Obtain the keyword count and keyword acquisition time included in the daily behavior attribute parameters, wherein the keyword count is the number of times the keyword appears in the keyword level to which it belongs;

[0023] Calculate the product of the number of times the keyword appears and the level weight corresponding to the keyword level to obtain a first weight; and, based on the keyword acquisition time, obtain the time interval to which the keyword belongs; obtain the number of times the keyword appears in the time interval to which it belongs, calculate the product of the number and the time weight corresponding to the time interval to obtain a second weight;

[0024] The sum of the first weight and the second weight is used as the weight of the keyword.

[0025] In addition, the method for generating a cultural travel plan according to one aspect of the present application further includes: after obtaining the cultural travel plan of the user from the plurality of cultural travel plan drafts, further including:

[0026] Generate an electronic garden tour table based on the cultural tourism plan;

[0027] Acquire instruction information input by the user when touring with reference to the electronic tour table, wherein the instruction information includes a node update parameter of a target cultural and tourism node;

[0028] Update the target cultural tourism node according to the node update parameter to obtain a backup electronic park tour table;

[0029] When the user indicates that he agrees to continue the cultural travel plan according to the backup electronic garden tour table, the backup electronic garden tour table is displayed to the user.

[0030] According to another aspect of the present application, a cultural tourism plan generation device is provided, comprising:

[0031] An acquisition module, used to acquire keywords related to tourism scenes and daily behavior attribute parameters of the keywords based on the collected daily behavior data representing the habits and interests of the user, wherein the daily behavior attribute parameters are used to represent the importance of the keywords;

[0032] A calculation module, used for calculating the weight of the keyword based on the daily behavior attribute parameters;

[0033] A prediction module, used to use a pre-trained large language model to infer the keywords and the weights to obtain multiple draft cultural and tourism plans;

[0034] A generation module is used to obtain the user's cultural travel plan from the multiple cultural travel plan drafts.

[0035] According to another aspect of the present application, a computer device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method of the above aspect.

[0036] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method of the above aspect is implemented.

[0037] According to another aspect of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method of the above aspect is implemented.

[0038] As will be described in detail below, according to a method, device, equipment, storage medium and program product for generating a cultural travel plan in an embodiment of the present application, by collecting daily behavior data that characterizes user habits and interests and extracting keywords therefrom, it is possible to obtain places or attractions that the user may be interested in, and then formulate a corresponding draft cultural travel plan for the user. When the user has a travel idea or need but cannot determine the travel location, the user can select the one he or she is interested in from multiple draft cultural travel plans, and a detailed cultural travel plan is generated for the location ultimately selected by the user, without the need for the user to plan or search by themselves, which is conducive to improving the user's travel experience.

[0039] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the technology as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0041] Figure 1 It is a flowchart illustrating the application of the method for generating a cultural tourism plan according to an embodiment of the present application.

[0042] Figure 2 is a flowchart illustrating an application of updating an electronic garden table according to an embodiment of the present application.

[0043] Figure 3 It is another flow chart illustrating the application of the method for generating a cultural tourism plan according to an embodiment of the present application.

[0044] Figure 4 It is a structural diagram illustrating a device for generating a cultural tourism plan according to an embodiment of the present application.

[0045] Figure 5 It is a schematic diagram illustrating the structure of a computer device according to an embodiment of the present application.

[0046] Figure 6 is a schematic diagram illustrating a computer program product according to an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application more obvious, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0048] In the prior art, cultural and tourism plans mostly rely on manual processing, that is, users search for target tourist cities, attractions, etc. and formulate corresponding travel plans. However, most users can only search for popular attractions in the target tourist cities on the Internet. These popular attractions are not all attractions that users are interested in, and relatively niche attractions that users are interested in may not be searchable. Therefore, manually formulated travel plans bring users a poor travel experience, low efficiency, and long time consumption. In addition, if the user only has the idea or demand of traveling, but has not yet determined the target tourist city or is not familiar with the target tourist city, it is also difficult to formulate a suitable cultural and tourism plan through manual processing.

[0049] The above describes the method, device, equipment, storage medium and program product for generating a cultural travel plan according to the embodiments of the present application with reference to the accompanying drawings. By collecting daily behavior data that characterizes user habits and interests and extracting keywords therefrom, it is possible to obtain places or attractions that the user may be interested in, and then formulate a corresponding draft cultural travel plan for the user. When the user has a travel idea or need but cannot determine the travel location, the user can select the one he or she is interested in from multiple draft cultural travel plans, and a detailed cultural travel plan is generated for the location finally selected by the user. The user does not need to plan or search by himself or herself, which is conducive to improving the user's travel experience.

[0050] To facilitate understanding of this embodiment, the cultural travel plan generation method disclosed in the embodiment of the present application is first introduced in detail. The execution subject of the cultural travel plan generation method provided in the embodiment of the present application is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal DiTital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the cultural travel plan generation method can be implemented by a processor calling a computer-readable instruction stored in a memory. In some possible implementations, the display terminal of the cultural travel plan generation method can be a mobile phone, a tablet (ipad) or a computer, etc.

[0051] like Figure 1As shown, it is a flow chart of a method for generating a cultural tourism plan provided in an embodiment of the present application, and the method includes S1-S4:

[0052] S1: Based on the collected daily behavior data that characterizes the user's habits and interests, obtain keywords related to the tourism scene and the daily behavior attribute parameters of the keywords.

[0053] Specifically, daily behavior data can be obtained by monitoring the apps that users frequently use, such as reading records, video viewing records, shopping records, etc. obtained from the apps, and extracting daily behavior data from these records. In actual applications, these records can also be obtained by deploying plug-ins in the apps that users frequently use.

[0054] Among them, the daily behavior attribute parameters are used to characterize the importance of keywords, such as the time of keyword acquisition, the number of keywords, etc.

[0055] Wherein, obtaining keywords includes the following steps:

[0056] S1.1 Extract first-level keywords related to tourism scenarios from daily behavior data.

[0057] For example, first-level keywords related to tourist scenes such as names of people, places, scenic spots, etc., such as Qin Shihuang, Xi'an, Terracotta Warriors, etc.

[0058] S1.2 uses a pre-trained large language model to generate secondary keywords related to the tourism scenes represented by the primary keywords, and generates tertiary keywords related to the tourism scenes represented by the secondary keywords.

[0059] Specifically, the pre-trained large language model can be an AIGC (AI Generated Content) model. The AIGC model can use artificial intelligence technology to generate content and automatically generate text, pictures, 3D models and codes, etc. For its relevant principles, please refer to the prior art. Input the first-level keywords into the AIGC model to obtain the second-level keywords output by the AIGC model; input the second-level keywords into the AIGC model to obtain the third-level keywords output by the AIGC model. Among them, the number of third-level keywords is greater than the number of second-level keywords, and the number of second-level keywords is greater than the number of first-level keywords. By generating multi-level keywords and extending the content that users are interested in, the success rate of capturing user interest points can be improved, which is conducive to tailoring cultural and travel plans for users and improving user satisfaction.

[0060] S1.3 Obtain keywords based on the primary keywords, the secondary keywords, and the tertiary keywords.

[0061] Specifically, the first-level keywords, second-level keywords and third-level keywords are used as keywords. It should be noted that the same keywords may exist in the first-level keywords, second-level keywords and third-level keywords. For example, the first-level keywords include "Xi'an" and "Terracotta Warriors", and the second-level keywords generated for "Terracotta Warriors" also include "Xi'an". Then the keyword "Xi'an" will exist at the first-level keyword and second-level keyword levels at the same time. For such keywords that appear repeatedly at multiple levels, only one can be extracted and the number of this keyword and the level to which it belongs can be recorded; for example: the keyword "Xi'an", the number is 5, of which 2 are first-level keywords and 3 are second-level keywords.

[0062] S2: Calculate the weight of keywords based on daily behavior attribute parameters.

[0063] The specific calculation method of weight is as follows:

[0064] Method 1, including S2.11-S2.13:

[0065] S2.11 obtains the number of keyword times included in the daily behavior attribute parameters, where the number of keyword times is the number of times the keyword appears in the keyword level to which it belongs.

[0066] This method takes the keyword "Qin Shi Huang" as an example, which appears 10 times (i.e., the number is 10). It appears 2 times in the first-level keywords, 3 times in the second-level keywords, and 5 times in the third-level keywords.

[0067] S2.12 Calculate the product of the keyword frequency and the level weight corresponding to the keyword level to obtain a first weight.

[0068] Specifically, the level weight corresponding to the keyword level can be a pre-configured weight, and the specific weight value can be selected according to actual needs. The embodiment of the present application assumes that the weight of the first-level keyword is 10, the weight of the second-level keyword is 6, and the weight of the third-level keyword is 3.

[0069] Then the first weights of the keyword "Qin Shi Huang" are 20, 18, and 15 respectively.

[0070] S2.13 takes the sum of the first weights as the weight of the keyword.

[0071] The weight of the keyword "Qin Shi Huang" is the sum of the first weights, 20+18+15=53, that is, the final weight is 53.

[0072] Method 2: including S2.21-S2.23:

[0073] S2.21 Based on the keyword acquisition time included in the daily behavior attribute parameters, obtain the time interval to which the keyword belongs.

[0074] The time interval can be, for example, this week, last week, the week before last... or today, yesterday, the day before yesterday... The specific time interval interval can be set based on actual needs. For the sake of convenience of explanation, this embodiment assumes that the closest keyword acquisition time is today, and the farthest is the 50th day before today (including the 50th day). At this time, today to the 10th day before today (including the 10th day) can be set as the first interval, the 11th day to the 20th day before today (including the 11th day and the 20th day) can be set as the second interval, the 21st day to the 30th day before today (including the 21st day and the 30th day) can be set as the third interval, the 31st day to the 40th day before today (including the 31st day and the 40th day) can be set as the fourth interval, and the 41st day to the 50th day before today (including the 41st day and the 50th day) can be set as the fifth interval.

[0075] In the case where the keywords include the first-level keywords, the second-level keywords, and the third-level keywords, take the keyword "Xi'an" as an example, as long as "Xi'an" appears in the first-level keywords, whether it appears in the second-level keywords and the third-level keywords, the keyword acquisition time of "Xi'an" is obtained from the daily behavior attribute parameters, and the time interval to which it belongs is determined according to the keyword acquisition time; if "Xi'an" does not appear in the first-level keywords, but only appears in the second-level keywords or the third-level keywords, it is considered that the time interval to which "Xi'an" belongs is the farthest interval, that is, the last week. For example, the number of "Xi'an" is 10, of which 4 appear in the first-level keywords, 3 appear in the second-level keywords, and 3 appear in the third-level keywords, then the keyword acquisition time of the 4 "Xi'an" that appear in the first-level keywords is obtained, and the most recent time is taken as the keyword acquisition time of the keyword "Xi'an". Assuming that the most recent time is the second day before today (that is, the day before yesterday), then the time interval to which the keyword "Xi'an" belongs is the first interval; for another example, the number of the keyword "Wang Changling" is 4, of which 2 appear in the second-level keywords and 2 appear in the third-level keywords, then the time interval to which the keyword "Wang Changling" belongs is the fifth interval.

[0076] S2.22 obtains the number of times the keyword appears in the time interval to which it belongs, calculates the product of the number of times and the time weight corresponding to the time interval, and obtains a second weight.

[0077] Specifically, the time weight corresponding to the time interval can be a pre-configured weight, and the specific weight value can be selected according to actual needs. The embodiment of the present application assumes that the weight of the first interval is 8, the weight of the second interval is 6, the weight of the third interval is 5, the weight of the fourth interval is 3, and the weight of the fourth interval is 1. If the keyword "Xi'an" appears 4 times in the first interval, 3 times in the second interval, and 5 times in the fourth interval, then the second weight of "Xi'an" in the first interval is 32, the second weight of the second interval is 18, and the second weight of the fourth interval is 15.

[0078] S2.23 takes the sum of the second weights as the weight of the keyword.

[0079] The weight of the keyword "Xi'an" is the sum of the second weight, 32+18+15=65, that is, the final weight is 65.

[0080] Method 3: Combine method 1 and method 2, calculate the sum of the first weight and the sum of the second weight of the keyword respectively, and take the sum of the two weights as the final weight of the keyword.

[0081] Taking the keyword "Xi'an" as an example, the final weight is 53+65=118.

[0082] Specifically, you can choose one of the three methods to calculate the weight of keywords, or you can choose a suitable method according to different application scenarios. For example, you can pre-set a time threshold and a quantity threshold, and determine whether to use method 1, method 2, or method 3 to calculate the weight based on whether the keyword meets the time threshold and the quantity threshold. For example, when the time threshold is set to 30 days and the quantity threshold is set to 1,000, the selection scenario is as follows:

[0083] (1) If all or most (for example, 60% or more) of the keywords are acquired within 30 days, it means that the difference in the acquisition time of the keywords is small. Then it is not very meaningful to consider the importance of keywords in the time dimension. In this case, method 1 can be used to calculate the weight of keywords.

[0084] (2) If the number of all or most (for example, 60% and above) keywords exceeds 1,000, for example, the same keyword appears repeatedly in the books that the user has read recently, resulting in an unreasonable increase in the number of keywords, then it is not very meaningful to consider the importance of keywords in terms of quantity. In this case, method 2 can be used to calculate the weight of keywords.

[0085] (3) If all or most (for example, 60% or more) of the keywords are acquired outside 30 days and the number does not exceed 1,000, it means that the acquisition time of the keywords varies greatly and the number is reasonable. In this case, method three can be selected to calculate the weight of the keywords.

[0086] (4) If all or most (e.g., 60% or more) of the keywords are acquired within 30 days and the number exceeds 1,000, then method 1 or method 2 may be selected to calculate the weight of the keywords. Further preferably, method 2 may be selected to calculate the weight of the keywords, and multiple time intervals may be set according to the time threshold (e.g., 30 days), for example, 10 days as one time interval, for a total of 3 time intervals; or 5 days as one time interval, for a total of 6 time intervals.

[0087] S3: Use a pre-trained large language model to infer keywords and weights to obtain multiple draft cultural and tourism plans.

[0088] Specifically, the keywords and weights are input into a pre-trained large language model, and the large language model outputs multiple draft cultural and tourism plans. Among them, the relevant principles of the large language model can be found in the prior art. The embodiment of this application specifically takes the AIGC model as an example. If the user may want to go to multiple places, the AIGC model can output a draft cultural and tourism plan for each place, or the AIGC model can output a draft cultural and tourism plan, and the draft includes multiple places that the user wants to go. For example, the draft cultural and tourism plan includes places and travel durations such as a three-day tour in Xi'an, a five-day tour in Hangzhou, and a three-day tour in Shanghai. Further preferably, when the user wants to go to multiple places, the places can be displayed to the user in descending order of weight according to the weight of the keyword, so that the user can choose the travel plan of interest.

[0089] S4: Obtain the user's cultural and tourism plan from multiple cultural and tourism plan drafts.

[0090] Specifically, the demand information input by the user into the AIGC model can be obtained, such as the desired location, duration, and cost, etc., and multiple cultural travel plans can be obtained from multiple draft cultural travel plans according to the user's needs. Assuming that the location entered by the user is Shanghai, the duration is 3 days, and the cost is less than 5,000 yuan, then the AIGC model can generate multiple cultural travel plans for Shanghai according to the user's needs. Each cultural travel plan may include different attractions in Shanghai and the order of visiting the attractions. Users can choose a cultural travel plan that suits them according to their interests.

[0091] In the embodiment of the present application, after obtaining the user's cultural travel plan from the plurality of cultural travel plan drafts, Figure 2 As shown, S5.1-5.4 are also included:

[0092] S5.1 Generate an electronic park tour schedule based on the cultural and tourism plan.

[0093] The electronic park schedule includes information on multiple cultural and tourism nodes (i.e. tourist attractions information), such as the order of visiting each cultural and tourism node, expected arrival time, expected stay time, expected departure time, check-in destination or location, whether reservations are required, the current number of visitors, transportation methods and time required between different cultural and tourism nodes, and other information.

[0094] S5.2 obtains instruction information input by the user when touring the park with reference to the electronic park tour table, where the instruction information includes node update parameters of the target cultural and tourism node.

[0095] The indication information includes, for example, skipping, deleting or marking the target cultural and tourism node, adding the target cultural and tourism node, etc. The node update parameter is used to characterize the updated status of the target cultural and tourism node, such as skipping, deleting or marking, etc.

[0096] S5.3 updates the target cultural and tourism node according to the node update parameters and obtains a backup electronic park schedule.

[0097] Updating the target cultural and tourism node can specifically be skipping, deleting, marking, etc. For example, when the user is executing the electronic garden table, the play time at the previous cultural and tourism node is too long, or the user has an emergency and cannot go to a remaining cultural and tourism node (i.e., the target cultural and tourism node), then the user can operate on the electronic garden table, delete or mark the target cultural and tourism node (for example, gray out the target cultural and tourism node), indicating that the target cultural and tourism node is skipped, and then updated to a new electronic garden table (i.e., a backup electronic garden table). For example, if the target cultural and tourism node is outdoors, and the user's terminal device (such as a mobile phone) detects that it is about to rain, in order to avoid affecting the user's play experience, the target cultural and tourism node can be marked (for example, marked with a red warning), and an alternative cultural and tourism node is generated for the user, and then a backup electronic garden table is generated.

[0098] S5.4 If the user indicates that he agrees to continue the cultural travel plan according to the alternative electronic garden tour schedule, the alternative electronic garden tour schedule is displayed to the user.

[0099] If the user confirms the selection of the alternative cultural and tourism node, it means that the user indicates and agrees to continue the cultural and tourism plan according to the alternative electronic garden tour table, and the alternative electronic garden tour table is displayed to the user.

[0100] like Figure 3 As shown, it is a flowchart of the method for generating a cultural tourism plan provided in an embodiment of the present application, and the method includes steps 1-11:

[0101] Step 1: Collect daily behavioral data that characterizes the user's habits and interests.

[0102] The embodiment of the present application is explained by taking the user's daily reading content as an example. It is assumed that the user has recently read history books, and the daily behavior data is the recorded points of interest of the user's reading, such as the content marked or annotated by the user.

[0103] Step 2: Extract primary keywords through daily behavior data.

[0104] For example, "Qin Shi Huang", "Xianyang", etc.

[0105] Step 3: Input the primary keywords into the AIGC model to generate secondary keywords.

[0106] For example, the second-level keywords generated by "Qin Shi Huang" include "Terracotta Warriors" and "Xi'an", and the second-level keywords generated by "Xianyang" include "Shaanxi" and "Qin Shi Huang".

[0107] Step 4: Input the secondary keywords into the AIGC model to generate tertiary keywords.

[0108] For example, the third-level keywords generated by "Xi'an" include "Wang Changling" and "Big Wild Goose Pagoda".

[0109] It should be noted that the number of first-level keywords, second-level keywords and third-level keywords increases successively.

[0110] Step 5: Calculate the weight of the keyword. The specific calculation method is as follows:

[0111] Method 1, including S2.11-S2.13:

[0112] S2.11 obtains the number of keyword times included in the daily behavior attribute parameters, where the number of keyword times is the number of times the keyword appears in the keyword level to which it belongs.

[0113] This method takes the keyword "Qin Shi Huang" as an example, which has 8 keyword occurrences (i.e., 8 in number), 4 of which appear in the first-level keywords, 2 times in the second-level keywords, and 2 times in the third-level keywords.

[0114] S2.12 Calculate the product of the keyword frequency and the level weight corresponding to the keyword level to obtain a first weight.

[0115] Specifically, the level weight corresponding to the keyword level can be a pre-configured weight, and the specific weight value can be selected according to actual needs. The embodiment of the present application assumes that the weight of the first-level keyword is 10, the weight of the second-level keyword is 6, and the weight of the third-level keyword is 3.

[0116] Then the first weights of the keyword "Qin Shi Huang" are 40, 12, and 6 respectively.

[0117] S2.13 takes the sum of the first weights as the weight of the keyword.

[0118] The weight of the keyword "Qin Shi Huang" is the sum of the first weights, 40+12+6=58, that is, the final weight is 58.

[0119] Method 2: including S2.21-S2.23:

[0120] S2.21 Based on the keyword acquisition time included in the daily behavior attribute parameters, obtain the time interval to which the keyword belongs.

[0121] This embodiment assumes that the most recent acquisition time of the keyword "Qin Shi Huang" is today, and the farthest is the 50th day before today (including the 50th day). At this time, today to the 10th day before today (including the 10th day) can be set as the first interval, the 11th day to the 20th day before today (including the 11th day and the 20th day) can be set as the second interval, and the 21st day to the 30th day before today (including the 21st day and the 30th day) can be set as the third interval, and the fourth and fifth intervals can be set similarly.

[0122] When the keywords include first-level keywords, second-level keywords, and third-level keywords, taking the keyword "Qin Shi Huang" as an example, as long as "Qin Shi Huang" appears in the first-level keywords, no matter whether it appears in the second-level keywords and the third-level keywords, the keyword acquisition time of "Qin Shi Huang" is obtained from the daily behavior attribute parameters, and the time interval to which it belongs is judged according to the keyword acquisition time; if "Qin Shi Huang" does not appear in the first-level keywords, but only appears in the second-level keywords or the third-level keywords, it is considered that the time interval to which "Qin Shi Huang" belongs is the farthest interval, that is, last week. For example, there are 10 "Qin Shi Huang" keywords, 4 of which appear in the first-level keywords, 3 appear in the second-level keywords, and 3 appear in the third-level keywords. Then, the keyword acquisition time of the 4 "Qin Shi Huang" keywords that appear in the first-level keywords is obtained, and the most recent time is used as the keyword acquisition time of the keyword "Xi'an". Assuming that the most recent time is the second day before today (that is, the day before yesterday), the time interval to which the keyword "Qin Shi Huang" belongs is the first interval; for another example, there are 4 keywords "Wang Changling" keywords, 2 of which appear in the second-level keywords, and 2 appear in the third-level keywords. Then, the time interval to which the keyword "Wang Changling" belongs is the fifth interval.

[0123] S2.22 obtains the number of times the keyword appears in the time interval to which it belongs, calculates the product of the number of times and the time weight corresponding to the time interval, and obtains a second weight.

[0124] Specifically, the time weight corresponding to the time interval can be a pre-configured weight, and the specific weight value can be selected according to actual needs. The embodiment of the present application assumes that the weight of the first interval is 8, the weight of the second interval is 6, the weight of the third interval is 5, the weight of the fourth interval is 3, and the weight of the fourth interval is 1. If the keyword "Qin Shi Huang" appears 4 times in the first interval, 3 times in the second interval, and 5 times in the fourth interval, then the second weight of "Xi'an" in the first interval is 32, the second weight of the second interval is 18, and the second weight of the fourth interval is 15.

[0125] S2.23 takes the sum of the second weights as the weight of the keyword.

[0126] The weight of the keyword "Qin Shi Huang" is the sum of the second weights, 32+18+15=65, that is, the final weight is 65.

[0127] Method 3: Combine method 1 and method 2, calculate the sum of the first weight and the sum of the second weight of the keyword respectively, and take the sum of the two weights as the final weight of the keyword.

[0128] Taking the keyword "Qin Shi Huang" as an example, the final weight is 58+65=113.

[0129] Specifically, you can choose one of the three methods to calculate the weight of keywords, or you can choose a suitable method according to different application scenarios. For example, you can pre-set the time threshold and quantity threshold, and choose method 1, method 2 or method 3 to calculate the weight according to whether the keyword meets the time threshold and quantity threshold. For example, the time threshold is set to 12 days and the quantity threshold is set to 1000. The selection scenarios are as follows:

[0130] (1) If the keyword acquisition time of all or most (for example, 80% or more) keywords is within 12 days, it means that the difference in keyword acquisition time is small. Then it is not very meaningful to consider the importance of keywords in the time dimension. At this time, you can choose method 1 to calculate the weight of keywords.

[0131] (2) If the number of all or most (e.g. 80% and above) keywords exceeds 1,000, for example, the same keyword appears repeatedly in the books the user has read recently, resulting in an unreasonable increase in the number of keywords, then it is not very meaningful to consider the importance of keywords in terms of quantity. In this case, method 2 can be used to calculate the weight of keywords.

[0132] (3) If all or most (e.g. 80% and above) of the keywords are acquired outside 12 days and the number does not exceed 1,000, it means that the acquisition time of the keywords varies greatly and the number is reasonable. In this case, method 3 can be selected to calculate the weight of the keywords.

[0133] (4) If the keyword acquisition time of all or most (e.g., 80% or more) keywords is within 12 days and the number exceeds 1000, method 1 or method 2 can be selected to calculate the weight of the keyword. More preferably, method 2 is selected to calculate the weight of the keyword, and multiple time intervals can be set according to the time threshold (e.g., 12 days), for example, 4 days as one time interval, a total of 3 time intervals; or 3 days as one time interval, a total of 4 time intervals.

[0134] It should be noted that in the above four scenarios, whether the quantity or time meets the threshold requirement can be determined based on all keywords, or only based on the primary keywords.

[0135] Step 6: Display the keywords in descending order according to the weight.

[0136] The smaller the weight of a keyword, the less interested the user is. Therefore, the keywords are displayed in descending order to facilitate users to filter keywords and delete some keywords with small weights and that users are not interested in, so as to improve the accuracy of AIGC model prediction.

[0137] Step 7: Input the keywords and weights filtered by users into the AIGC model, and the AIGC model outputs multiple draft cultural and tourism plans.

[0138] Among them, the user may want to go to multiple places. The AIGC model can output a draft cultural and tourism plan for each place, or the AIGC model can output a draft cultural and tourism plan, which includes multiple places the user wants to go. For example, the draft cultural and tourism plan includes a three-day tour in Xi'an, a five-day tour in Hangzhou, a three-day tour in Shanghai and other places and travel durations.

[0139] Step 8: Obtain the demand information input by the user. The AIGC model determines the draft cultural and tourism plan based on the demand information and generates the user's cultural and tourism plan.

[0140] Demand information may include the place the user wants to go, duration, cost, museum-based, scenic-based, surrounding cities, etc. For example, if a user chooses a five-day tour in Hangzhou with a budget of less than 5,000 yuan, he can go to surrounding cities such as Suzhou and Shanghai. The cultural tourism plan includes multiple cultural tourism nodes (i.e. tourist attractions), most of which are located in Hangzhou, and a small number of cultural tourism nodes are located in Suzhou and Shanghai. Each cultural tourism node information contains corresponding keywords, introduction, total area, estimated tour duration, etc., and can also be accompanied by multiple punch-in targets. Users can check their favorite cultural tourism nodes according to their interests, and can also enter other information, such as wanting to visit more martyrs' tombs, preferring taxis as a means of transportation, etc. According to the user's check information and input information, the travel content is improved and the cultural tourism plan is confirmed.

[0141] Step 9: Generate an electronic tour schedule based on the user’s cultural and travel plan.

[0142] The electronic park tour table includes multiple cultural and tourism node information (i.e. tourist attraction information), for example:

[0143] (1) Information such as the order of visiting each cultural and tourism node, the transportation methods and time required between different cultural and tourism nodes, etc.

[0144] (2) Estimated arrival time. After arriving, the user can check the "Sign in" button to register the actual arrival time so as to update the electronic tour table and optimize the AIGC model.

[0145] (3) Estimated departure time. When the user leaves, he or she can check the "Sign out" button to register the actual departure time so as to update the electronic tour table and optimize the AIGC model.

[0146] (4) Whether an appointment is required. If an appointment is required, the appointment method must also be included.

[0147] (5) Current number of visitors and recommendation index.

[0148] (6) Recommendations for nearby accommodation and restaurants.

[0149] (7) Check-in destination or location.

[0150] The check-in target may be a keyword, picture description or other things in the book reading. After the user arrives at the cultural and tourism node and finds the check-in target, he can check in by taking photos and AI recognition. If it meets the requirements, it is considered a successful check-in. For example, the user plans to take a group photo at the Terracotta Warriors and Horses Museum in Xi'an at 1 pm. After the photo is uploaded, AI recognizes that the person in the photo is the user and the scene is the Terracotta Warriors, and then marks the check-in as successful. For another example, the user plans to go to the Xi'an Library at 5 pm to find the book "The Great Qin Empire" and take a photo. After the photo is uploaded, AI recognizes that the person in the photo is the user and the book is "The Great Qin Empire", and then marks the check-in as successful.

[0151] Step 10: Update the electronic garden schedule.

[0152] The indication information input by the user when touring the park with reference to the electronic park tour table is obtained, and the indication information includes the node update parameter of the target cultural and tourism node. The node update parameter is used to represent the updated state of the target cultural and tourism node, such as skipping, deleting or marking, for example:

[0153] (1) When a user is late, takes a long time to visit a single attraction, or has a change of plan, the entire target cultural and tourism node can be skipped, the skipped target cultural and tourism node can be grayed out, and the electronic park schedule can be updated.

[0154] (2) During the electronic tour schedule, if it rains, closes, or traffic jams occur, which affect the user's experience of the target cultural and tourism node, the target cultural and tourism node can be marked (for example, marked with a red warning), the remaining tour time and cultural and tourism nodes can be adjusted, and a backup plan can be generated in real time. For example, after visiting the library, the next cultural and tourism node is an open-air museum, but the weather forecast shows that it will rain in 30 minutes, which will affect the user's normal tour. At this time, the open-air museum can be marked with a red warning to inform the user of the situation. If the user confirms and chooses to switch to the alternative plan, the AIGC model generates an alternative city museum scene in real time and connects it to the library itinerary.

[0155] In addition, users can also update the electronic park schedule by inputting content, for example: I want to play in this cultural and tourism node for one more hour; it is difficult to get a taxi here, please help me choose public transportation, etc.

[0156] Step 11: Optimize the AIGC model based on the evaluation content input by the user.

[0157] After the cultural travel plan is completed, the user can evaluate the overall plan or each cultural travel node (including transportation methods and climate). For example, the overall trip is very satisfactory, but the end time is too late, I want to go back to bed early; or the accommodation and attractions are too far away, I want to be closer; or I get up too early in the morning, I want to sleep a little longer. The AIGC model will use these contents as inputs, optimize and train them again, and improve the user experience. In addition, the generated cultural travel plan and electronic park schedule can also be exported so that users can share them on social media.

[0158] According to another aspect of the embodiment of the present application, a device for generating a cultural tourism plan is provided, such as Figure 4 As shown, the device comprises:

[0159] The acquisition module 101 is used to acquire keywords related to the tourism scene and daily behavior attribute parameters of the keywords based on the collected daily behavior data representing the user's habits and interests, and the daily behavior attribute parameters are used to represent the importance of the keywords.

[0160] The calculation module 102 is used to calculate the weight of the keyword based on the daily behavior attribute parameters.

[0161] The prediction module 103 is used to use a pre-trained large language model to infer the keywords and the weights to obtain multiple draft cultural and tourism plans.

[0162] The generating module 104 is used to obtain the cultural travel plan of the user from the multiple cultural travel plan drafts.

[0163] In one or more embodiments, the acquisition module 101 is used to:

[0164] Extracting primary keywords related to tourism scenarios from the daily behavior data;

[0165] Using the preset large language model, generating secondary keywords related to the tourism scene represented by the primary keywords, and generating tertiary keywords related to the tourism scene represented by the secondary keywords;

[0166] Based on the primary keyword, the secondary keyword and the tertiary keyword, the keyword is obtained.

[0167] In one or more embodiments, the computing module 102 is configured to:

[0168] Obtaining the number of keywords included in the daily behavior attribute parameter, where the number of keywords is the number of times the keyword appears in the keyword level to which it belongs;

[0169] Calculate the product of the keyword frequency and the level weight corresponding to the keyword level to obtain a first weight;

[0170] The sum of the first weights is used as the weight of the keyword.

[0171] In one or more embodiments, the computing module 102 is configured to:

[0172] Based on the keyword acquisition time included in the daily behavior attribute parameter, acquiring the time interval to which the keyword belongs;

[0173] Obtaining the number of times the keyword appears in the time interval to which it belongs, and calculating the product of the number and the time weight corresponding to the time interval to obtain a second weight;

[0174] The sum of the second weights is used as the weight of the keyword.

[0175] In one or more embodiments, the computing module 102 is configured to:

[0176] Obtain the keyword count and keyword acquisition time included in the daily behavior attribute parameters, wherein the keyword count is the number of times the keyword appears in the keyword level to which it belongs;

[0177] Calculate the product of the number of times the keyword appears and the level weight corresponding to the keyword level to obtain a first weight; and, based on the keyword acquisition time, obtain the time interval to which the keyword belongs; obtain the number of times the keyword appears in the time interval to which it belongs, calculate the product of the number and the time weight corresponding to the time interval to obtain a second weight;

[0178] The sum of the first weight and the second weight is used as the weight of the keyword.

[0179] The cultural and tourism plan generating device is also used for: after obtaining the cultural and tourism plan of the user from the multiple cultural and tourism plan drafts, generating an electronic garden tour table based on the cultural and tourism plan; when the user is touring with reference to the electronic garden tour table, obtaining indication information, the indication information being used to indicate updated cultural and tourism parameters of the target cultural and tourism node; updating the target cultural and tourism node according to the updated cultural and tourism parameters to obtain a backup electronic garden tour table; and when the user indicates that he agrees to continue the cultural and tourism plan according to the backup electronic garden tour table, displaying the backup electronic garden tour table to the user.

[0180] The cultural and tourism plan generation device for a heterogeneous network provided in the embodiment of the present application and the cultural and tourism plan generation method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0181] The present application also provides a computer device to execute the above-mentioned cultural tourism plan generation method. Figure 5 It shows a schematic diagram of a computer device provided by some embodiments of the present application. Figure 5 As shown, the computer device 8 includes: a processor 800, a memory 801, a bus 802 and a communication interface 803, and the processor 800, the communication interface 803 and the memory 801 are connected via the bus 802; the memory 801 stores a computer program that can be run on the processor 800, and when the processor 800 runs the computer program, it executes the cultural and tourism plan generation method provided in any of the aforementioned embodiments of the present application.

[0182] The memory 801 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the device network element and at least one other network element is realized through at least one communication interface 803 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0183] The bus 802 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 801 is used to store programs, and the processor 800 executes the program after receiving an execution instruction. The cultural tourism plan generation method disclosed in any implementation of the embodiment of the present application may be applied to the processor 800, or implemented by the processor 800.

[0184] The processor 800 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 800. The above processor 800 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a ready-made programmable gate array (FPTA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 801, and the processor 800 reads the information in the memory 801 and completes the steps of the above method in combination with its hardware.

[0185] The computer device provided in the embodiment of the present application and the cultural tourism plan generation method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0186] An embodiment of the present application also provides a computer-readable storage medium corresponding to the cultural and tourism plan generation method provided in the aforementioned embodiment. The computer-readable storage medium is a CD on which a computer program (i.e., a computer program product) is stored. When the computer program is run by a processor, it will execute the cultural and tourism plan generation method provided in any of the aforementioned embodiments.

[0187] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0188] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the cultural tourism plan generation method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0189] The present application also provides a computer program product. Figure 6 The computer program product 600 carries a program code, namely a computer program 601. The instructions included in the computer program 601 can be used to execute the steps of the cultural tourism plan generation method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0190] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0191] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0192] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0193] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0194] It should also be noted that in the system and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0195] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the techniques of the teachings defined by the appended claims. Furthermore, the scope of the claims of this application is not limited to the specific aspects of the processes, machines, manufactures, compositions, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions, means, methods, or actions within their scope.

[0196] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0197] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for generating a cultural tourism plan, characterized in that: include: Based on the collected daily behavior data representing the user's habits and interests, obtain keywords related to the travel scene and daily behavior attribute parameters of the keywords, wherein the daily behavior attribute parameters are used to represent the importance of the keywords; Calculating the weight of the keyword based on the daily behavior attribute parameters; A pre-trained large language model is used to infer the keywords and the weights to obtain multiple draft cultural tourism plans; Obtain the cultural travel plan of the user from the multiple cultural travel plan drafts.

2. The method for generating a cultural tourism plan according to claim 1, characterized in that: Based on the collected daily behavior data that characterizes user habits and interests, keywords related to travel scenarios are obtained, including: Extracting primary keywords related to tourism scenarios from the daily behavior data; Using the preset large language model, generating secondary keywords related to the tourism scene represented by the primary keywords, and generating tertiary keywords related to the tourism scene represented by the secondary keywords; Based on the primary keyword, the secondary keyword and the tertiary keyword, the keyword is obtained.

3. The method for generating a cultural tourism plan according to claim 1, characterized in that: Calculating the weight of the keyword based on the daily behavior attribute parameter includes: Obtaining the number of keywords included in the daily behavior attribute parameter, where the number of keywords is the number of times the keyword appears in the keyword level to which it belongs; Calculate the product of the keyword frequency and the level weight corresponding to the keyword level to obtain a first weight; The sum of the first weights is used as the weight of the keyword.

4. The method for generating a cultural tourism plan according to claim 1, characterized in that: Calculating the weight of the keyword based on the daily behavior attribute parameter includes: Based on the keyword acquisition time included in the daily behavior attribute parameter, acquiring the time interval to which the keyword belongs; Obtaining the number of times the keyword appears in the time interval to which it belongs, and calculating the product of the number and the time weight corresponding to the time interval to obtain a second weight; The sum of the second weights is used as the weight of the keyword.

5. The method for generating a cultural tourism plan according to claim 1, characterized in that: Calculating the weight of the keyword based on the daily behavior attribute parameter includes: Obtain the keyword count and keyword acquisition time included in the daily behavior attribute parameters, wherein the keyword count is the number of times the keyword appears in the keyword level to which it belongs; Calculate the product of the number of times the keyword appears and the level weight corresponding to the keyword level to obtain a first weight; and, based on the keyword acquisition time, obtain the time interval to which the keyword belongs; obtain the number of times the keyword appears in the time interval to which it belongs, calculate the product of the number and the time weight corresponding to the time interval to obtain a second weight; The sum of the first weight and the second weight is used as the weight of the keyword.

6. The method for generating a cultural tourism plan according to claim 1, characterized in that: After obtaining the cultural travel plan of the user from the plurality of draft cultural travel plans, the method further includes: Generate an electronic garden tour table based on the cultural tourism plan; Acquire instruction information input by the user when touring with reference to the electronic tour table, wherein the instruction information includes a node update parameter of a target cultural and tourism node; Update the target cultural tourism node according to the node update parameter to obtain a backup electronic park tour table; When the user indicates that he agrees to continue the cultural travel plan according to the backup electronic garden tour table, the backup electronic garden tour table is displayed to the user.

7. A device for generating a cultural tourism plan, characterized in that: include: An acquisition module, used to acquire keywords related to tourism scenes and daily behavior attribute parameters of the keywords based on the collected daily behavior data representing the habits and interests of the user, wherein the daily behavior attribute parameters are used to represent the importance of the keywords; A calculation module, used for calculating the weight of the keyword based on the daily behavior attribute parameters; A prediction module, used to use a pre-trained large language model to infer the keywords and the weights to obtain multiple draft cultural and tourism plans; A generation module is used to obtain the user's cultural travel plan from the multiple cultural travel plan drafts.

8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images