CN117372946A - Tourist group tourist behavior identification method - Google Patents
Tourist group tourist behavior identification method Download PDFInfo
- Publication number
- CN117372946A CN117372946A CN202311208043.4A CN202311208043A CN117372946A CN 117372946 A CN117372946 A CN 117372946A CN 202311208043 A CN202311208043 A CN 202311208043A CN 117372946 A CN117372946 A CN 117372946A
- Authority
- CN
- China
- Prior art keywords
- tourist
- group
- tourists
- moment
- behavior
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 230000006399 behavior Effects 0.000 claims abstract description 64
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 35
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000005755 formation reaction Methods 0.000 claims description 32
- 230000000694 effects Effects 0.000 claims description 20
- 230000000295 complement effect Effects 0.000 claims description 19
- 239000000463 material Substances 0.000 abstract description 4
- 230000000284 resting effect Effects 0.000 description 4
- 230000005484 gravity Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a tourist group tourist behavior identification method, which comprises the following steps: acquiring the track data of the group following and preprocessing; identifying whether the tourist group is a longitudinal team formation according to the tourist group tourist distribution characteristics, if so, further identifying the riding behavior, the walking behavior and the queuing behavior of the tourist; identifying whether the tourist group is a round formation, if so, further identifying the listening and speaking behaviors and dining behaviors of the tourist; and identifying whether the tourist group is a distributed formation, and if so, further identifying the rest behavior and shopping behavior of the tourist. The tourist group tourist behavior recognition method provided by the method can recognize the tourist group tourist behavior according to the tourist group track, and is convenient for scenic spots to adjust service supply, allocate manpower and material resources and the like according to the overall tourist group tourist behavior condition.
Description
Technical Field
The invention relates to the technical field of space-time big data application, in particular to a tourist group tourist behavior identification method.
Background
In recent years, with the sustainable development of national economy and the continuous improvement of living standard of people, the desire of people to travel is higher and higher. Many guests travel by reporting travel groups (following the group's tour). After reaching the attraction, guest activities generally include dining, riding, viewing (walking), queuing, listening to tour guide explanation (listening and speaking), shopping, resting, and the like. From the general perspective of the travel group, different behaviors may have different guest distribution characteristics. When riding, tourists sit in the front-back and left-right order, and tourist groups present a longitudinal team formation; similarly, when queuing, a column formation is also presented. When dining, tourists sit around the dining table, and tourists take round formations; similarly, when listening to tour guide instructions, guests generally wrap around the tour guide perimeter and also present a circular formation. When resting, tourists are generally close to familiar relatives and friends and are far away from other tourists, and large dispersion and small gathering (distributed formation) is presented; similarly, when shopping, tourists generally also communicate with a business volume of familiar relatives and friends.
Knowing tourist group tourist behavior is convenient for the scenic spot to master the whole running state, and then is convenient for the scenic spot to adjust service supply in time, allocate manpower and material resources and the like. If tourists of more tourists are queued at a certain scenic spot, the scenic spot should be drained and guided in time to prevent congestion; if tourists of more tourists take meals in a restaurant, the scenic spot should be allocated with food raw materials in time.
Currently, high-precision positioning service technology is mature gradually, and for example, a thousand-finding position can provide centimeter-level positioning service by adopting RTK technology. Patent document 2023106167322 discloses a tourist group type identification method based on big track data, which identifies whether tourists have staff members by analyzing the track data, and if the staff members have the staff members, further identifies whether the group type is a group following tour (tourist group), but the method cannot identify the tourist group tourist behavior. Therefore, how to use the tourist group track data to identify the tourist behavior of the tourist group, so that the scenic spot can conveniently adjust service supply, allocate manpower and material resources and the like in time is a problem to be solved urgently by the person skilled in the art.
Disclosure of Invention
The invention aims to provide a tourist group tourist behavior identification method for solving the problems encountered in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a tourist group tourist behavior identification method comprises the following steps:
s1: acquiring trace data of a travel group, and preprocessing to generate trace data of the travel group;
s2: identifying whether the tourist group is a team formation or not according to the tourist group tourist distribution characteristics, if so, further identifying the riding behavior, the walking behavior and the queuing behavior of the tourist group tourist;
s3: according to the distribution characteristics of tourists of the tourists, whether the tourists are round formations or not is identified, and if so, the listening and speaking behaviors and dining behaviors of the tourists are further identified;
s4: and (3) identifying whether the tourist group is a distributed formation according to the distribution characteristics of tourist group tourists, and if so, further identifying the rest behaviors and shopping behaviors of the tourist group tourists.
Further, in the step S1, the following group track is formed by a series of tourist track points, and the track points include tourist group numbers, tourist numbers, tour guide marks, time and coordinate information.
Further, the specific pretreatment step in the step S1 is as follows:
s11: extracting tourist track points with the same tourist group number and marking the tourist track points as tourist group track data;
s12: and calculating the activity speed of the tourist group at each moment according to the barycenter coordinates of the tourist group at each moment and the corresponding previous moment.
Further, the specific steps in the step S2 are as follows:
s21: connecting a tourist coordinate in each moment with other tourist coordinates, marking the tourist coordinate as a connecting direction, calculating an included angle and a complementary angle between each connecting direction and other connecting directions, counting the times that the included angle or the complementary angle is smaller than a preset included angle threshold value, marking the times as the included angle, marking the connecting direction corresponding to the maximum included angle times as a longitudinal direction, and marking other tourists of which the included angle or the complementary angle between the connecting direction and the longitudinal direction is smaller than a preset included angle threshold value as the same longitudinal tourists;
s22: repeating the step S21, and identifying the direction of the tourist and the tourist in the same team except the tourist and the tourist in the same team in each moment;
s23: calculating an included angle and a complementary angle between the longitudinal team directions in the tourist group at each moment;
s24: if the included angle or the complement angle between the longitudinal teams at a certain moment is smaller than the preset included angle threshold value, the tourist group is the formation of the longitudinal teams at the moment;
s25: if the activity speed of the tourist group is greater than the preset walking speed upper limit, the tourist group tourist is in riding behavior at the moment;
s26: if the activity speed of the tourist group is smaller than the upper limit of the preset walking speed and the activity speed of the tourist group is larger than the lower limit of the preset walking speed, the tourist group tourist is walking at the moment;
s27: if the activity speed of the tourist group is smaller than the preset walking speed lower limit, the tourist group tourist is in queuing.
Further, the specific steps in the step S3 are as follows:
s31: calculating the sum of the distances between each tourist coordinate and other tourist coordinates in the tourist group at each moment, marking the sum as the total distance among the tourists, counting the average value of the total distances among the tourists, and marking the average total distance among the tourists;
s32: if the total distance between all tourists in the tourist group at a certain moment is larger than the product of the average total distance between the tourists and the lower limit of the ratio of the preset distance and smaller than the product of the average total distance between the tourists and the upper limit of the ratio of the preset distance, the tourist group at the moment is in a round formation;
s33: if the tour guide personnel are positioned in the round formation of the tourist group, the tourist group tourist is in listening and speaking behaviors at the moment, and otherwise, is dining behaviors.
Further, the specific steps in the step S4 are as follows:
s41: calculating the nearest distance between each tourist coordinate and other tourist coordinates in each time tourist group, counting the average value of the nearest distances of each tourist, and marking the average nearest distance as the average nearest distance of the tourists;
s42: counting the maximum value and the minimum value of the transverse and longitudinal coordinates of each tourist in each time tourist group, further generating an external rectangle of each tourist coordinate, and calculating the area of the external rectangle;
s43: the nearest neighbor index of tourists in the tourist group at each moment is calculated, and the calculation formula is as follows:
NNI＝D/[0.5×(A/n) 0.5 ]
wherein NNI is nearest neighbor index, D is average nearest distance of tourists, A is external rectangular area, n is number of tourists in tourist group;
s44: if the nearest neighbor index at a certain moment is smaller than 1, the tourist group at the moment is in a distributed formation;
s45: if the ratio of tourists with the changed coordinates is smaller than the preset ratio threshold value, the tourists with the tourists group at the moment are at rest, otherwise, the tourists with the tourists group at the moment are shopping.
Compared with the prior art, the invention has the beneficial effects that:
the tourist behavior recognition method can recognize the behaviors of the tourist, such as riding, walking, queuing, listening and speaking, dining, resting, shopping and the like, according to the tourist track. By identifying tourist group tourist behaviors, the scenic spot is convenient to adjust service supply, allocate manpower and material resources and the like in time.
Drawings
FIG. 1 is a schematic flow chart of a tourist group tourist behavior recognition method provided by the invention;
FIG. 2 is a schematic illustration of a travel group column formation of the present invention;
FIG. 3 is a schematic view of a circular team of tourist clusters according to the present invention, (a) guest listening and speaking behavior, (b) guest dining behavior;
FIG. 4 is a schematic illustration of a travel group collection and distribution formation of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In this embodiment, a scenic spot is taken as an example to describe the implementation of the present invention, and the following will specifically describe the implementation steps of identifying tourist behavior of tourist groups according to the present invention with reference to this example:
s1: and acquiring the following group track data, and preprocessing to generate the traveling group track data. The group following track is from the processing result of the high-precision positioning track data, and is composed of a series of tourist track points, wherein the track points comprise tourist group numbers, tourist numbers, tour guide marks, time and coordinate information, the time precision of the data is 1 second, the space precision is 0.1 meter, and the coordinate system in the embodiment is a CGCS2000_3_Degree_GK_CM_120E projection coordinate system.
Specifically, the following-bolus trajectory data is shown in table 1.
Table 1 track data table for group travel (projection coordinates)
The pretreatment in the step S1 comprises the following specific steps:
s11: and extracting tourist track points with the same tourist cluster number, and recording the tourist track points as tourist cluster track data.
Specifically, since the travel group type is identified in units of travel groups, it is necessary to group travel following trajectory data by travel group. And extracting tourist track points with the same tourist group number (such as E group) and recording the tourist track points as tourist group track data.
S12: and calculating the activity speed of the tourist group at each moment according to the barycenter coordinates of the tourist group at each moment and the corresponding previous moment.
Specifically, at 09:11:00, the barycentric coordinates of the E bolus of the tourist are (459354.43923232.6), at 09:11:01, and the barycentric coordinates are (459356.9,3923235.1), and the movement speed of the E bolus at 09:11:01 is 3.54 m/s. Similarly, the activity rate of the travel mass at each time is calculated separately.
S2: and (3) identifying whether the tourist group is a team formation or not according to the tourist group tourist distribution characteristics, and if so, further identifying the riding behavior, the walking behavior and the queuing behavior of the tourist group tourist.
The specific steps in the step S2 are as follows:
s21: connecting a tourist coordinate in each moment with other tourist coordinates, marking the tourist coordinate as a connecting direction, calculating an included angle and a complementary angle between each connecting direction and other connecting directions, counting the times that the included angle or the complementary angle is smaller than a preset included angle threshold value, marking the times as the included angle, marking the connecting direction corresponding to the maximum included angle times as a longitudinal direction, and marking other tourists of which the included angle or the complementary angle between the connecting direction and the longitudinal direction is smaller than a preset included angle threshold value as the same longitudinal tourists.
Specifically, in 09:11:01, the direction of the line connecting the 301 tourist coordinate (459357.6,3923236.2) and the 302 tourist coordinate (459357.2,3923235.8) in the tourist group E is 45 degrees from south to west. Similarly, the directions of the links of the other guest coordinates and 302 guest coordinates are calculated, respectively, and the results are shown in table 2.
And calculating the included angle and the complementary angle of the reference direction and other connecting directions by taking the connecting direction of the 311 tourist coordinates and the 302 tourist coordinates as the reference direction, and counting the times that the included angle or the complementary angle is smaller than a preset included angle threshold (for example, 4 degrees) for 0 times in 09:11:01. Similarly, the line connecting direction of the coordinates of other tourists and the coordinates of the tourists is taken as the reference direction, and the statistical included angle or the supplementary angle is smaller than the threshold number of times of the preset included angle. The result shows that the included angle or the complement angle is smaller than the preset included angle threshold value for the maximum number of times (up to 4 times) by taking the connecting line direction of the 301 tourist coordinates and the 302 tourist coordinates as the reference direction, so that the longitudinal direction is 45 degrees in the south-west direction.
And (3) marking 301 tourists, 303 tourists, 304 tourists and the like corresponding to the fact that the included angle or the complement angle between the coordinate connecting line direction of 302 tourists and the longitudinal team direction is smaller than a preset included angle threshold value as the same longitudinal team tourists of 302 tourists in 09:11:01.
Similarly, the queue direction of 302 guests in the travel group E and the same queue guests at each time are identified separately.
Table 2 and other guest wiring direction table
S22: step S21 is repeated, and the direction of the tourist and the tourist in the same team except the tourist and the tourist in the same team in each moment are identified.
Specifically, in 09:11:01, step S21 is repeated to identify the queue direction and the same-queue guests of other guests in the group E except for 302 guests and the same-queue guests. Similarly, the guests' home direction and home tourists in the group E at each time except 302 are identified.
S23: and calculating the included angle and the supplementary angle between the longitudinal team directions in the tourist group at each moment.
Specifically, in 09:11:01, 2 longitudinal queues are arranged in total in the E group of the tourist group, the longitudinal queues are respectively 45 degrees in the south and west directions and 43.5 degrees in the north and east directions, the included angle between the 2 longitudinal queues is 178.5 degrees, and the complement angle is 1.5 degrees. Similarly, the included angle and the supplementary angle between the directions of the longitudinal strings of the tourist group E at each moment are calculated respectively.
S24: if the included angle or the complement angle between the longitudinal team directions at a certain moment is smaller than the preset included angle threshold value, the tourist group is the longitudinal team form at the moment.
Specifically, at 09:11:01, the supplementary angle between 2 longitudinal team directions of the tourist group E is smaller than the preset included angle threshold, and at 09:11:01, the tourist group E is in the longitudinal team form (fig. 2).
S25: if the activity speed of the tourist group is greater than the preset upper limit of walking speed, the tourist group tourist is in riding behavior at the moment.
Specifically, at 09:11:01, the activity speed of the tourist group E is 3.54 m/s and is greater than the preset upper limit of walking speed (such as 2 m/s), and at 09:11:01, the tourist group E tourist is in riding behavior.
S26: if the travel group activity speed is less than the preset walking speed upper limit and the travel group activity speed is greater than the preset walking speed lower limit, the travel group tourist is walking at the moment.
Specifically, at 09:27:32, the tourist group E is a column formation, the activity speed is 1.35 m/s, which is less than the upper limit of the preset walking speed and greater than the lower limit of the preset walking speed (for example, 0.8 m/s), and at 09:27:32, the tourist group E is a walking action.
S27: if the activity speed of the tourist group is smaller than the preset walking speed lower limit, the tourist group tourist is in queuing.
Specifically, at 09:32:08, the tourist group E is in the form of a column, the activity speed is 0.32 m/s and is smaller than the preset walking speed lower limit, and at 09:32:08, the tourist group E is in the form of queuing.
S3: and (3) identifying whether the tourist group is a round formation according to the distribution characteristics of tourists of the tourist group, and if so, further identifying the listening and speaking behaviors and dining behaviors of the tourists of the tourist group.
The specific steps in the step S3 are as follows:
s31: calculating the sum of the distances between each tourist coordinate and other tourist coordinates in the tourist group at each moment, marking the sum as the total distance among the tourists, counting the average value of the total distances among the tourists, and marking the average total distance among the tourists.
Specifically, in 09:57:12, the distance between the tourist F group and other tourist coordinates was calculated by using 401 tourists as the initial tourists, and the results are shown in Table 3. The sum of the distances of the guest coordinates and other guest coordinates is counted 401 to be 15.3 meters. Similarly, the total distance between guests of other guests in the travel group F group other than 401 are calculated, respectively. The average value of the total distance between tourists in the F group of the tourist group is 15.6 meters. Further, the total distance between tourists in the tourist group F at each moment is calculated respectively, and the average value is counted.
Table 3 distance Meter from other tourists
S32: if the total distance between all tourists in the tourist group at a certain moment is larger than the product of the average total distance between the tourists and the lower limit of the ratio of the preset distance and smaller than the product of the average total distance between the tourists and the upper limit of the ratio of the preset distance, the tourist group at the moment is in a round formation.
Specifically, at 09:57:12, calculate if the 401 guests in the travel group F satisfy: the total distance between tourists is greater than the average total distance between tourists multiplied by the lower limit of the ratio of the preset distance (such as 0.9) and the total distance between tourists is less than the average total distance between tourists multiplied by the upper limit of the ratio of the preset explanation distance (such as 1.1). The results indicate that 401 guests meet the requirements. Similarly, it is calculated whether the requirements are met by other guests in the travel group F group than 401. The results show that all tourists in the F group meet the requirements. Thus, at 09:57:12, the travel group F is a round formation.
S33: if the tour guide personnel are positioned in the round formation of the tourist group, the tourist group tourist is in listening and speaking behaviors at the moment, and otherwise, is dining behaviors.
Specifically, the distance between each guest coordinate and the barycentric coordinate was calculated at 09:57:12 with the barycentric coordinate of the tourist group F (459423.5,3923318.5), and the results are shown in Table 4. 400 tour guides have a coordinate (459423.5,3923318.6) that is 0.1 meters from the center of gravity coordinate. Since the distance between each tourist coordinate and the barycentric coordinate is greater than the distance between the tourist guide coordinate and the barycentric coordinate, 400 tourist guide personnel are located inside the tourist group formation, and the tourist group F tourist is in listening and speaking behaviors at 09:57:12, as shown in (a) in fig. 3. Similarly, at 12:13:24, 400 tourists in group F are not inside the circular formation, and at 12:13:24, group F tourists are dining, as shown in FIG. 3 (b).
Table 4 and distance meter for the center of gravity of tourist clusters
S4: and (3) identifying whether the tourist group is a distributed formation according to the distribution characteristics of tourist group tourists, and if so, further identifying the rest behaviors and shopping behaviors of the tourist group tourists.
The specific steps in the step S4 are as follows:
s41: and calculating the nearest distance between each tourist coordinate and other tourist coordinates in each time tourist group, counting the average value of the nearest distances of each tourist, and recording the average nearest distance of each tourist as the average nearest distance of the tourists.
Specifically, at 11:08:21, the distance between the coordinates of 501 tourists and the coordinates of 502 tourists in the G group is nearest, and the distance is 0.5 m. Similarly, the nearest distance of each guest coordinate to other guests in the group G except 501 guest is calculated. The average value of the nearest distance of each tourist in the G group of the tourist group is 0.6 meter through statistics. Further, the average nearest distance of tourists in the tourist group G at each moment is calculated.
S42: and counting the maximum value and the minimum value of the transverse and longitudinal coordinates of each tourist in the tourist group at each moment, further generating an external rectangle of each tourist coordinate, and calculating the area of the external rectangle.
Specifically, in the 11:08:21, the maximum value and the minimum value of the abscissa of each tourist in the tourist group G are 459675.2 and 459666.3 respectively, the maximum value and the minimum value of the ordinate are 3923131.5 and 3923124.1 respectively, and the maximum value and the minimum value of the abscissa are connected into an external rectangle of each tourist coordinate. The external rectangle is 8.9 meters long, 7.4 meters wide and 65.9 square meters in area. Similarly, the maximum value and the minimum value of the transverse and longitudinal coordinates of each tourist of the tourist group G at each moment are counted respectively, an external rectangle is generated, and the area of the external rectangle is calculated.
S43: the nearest neighbor index of tourists in the tourist group at each moment is calculated, and the calculation formula is as follows:
NNI＝D/[0.5×(A/n) 0.5 ]
wherein NNI is nearest neighbor index, D is average nearest distance of tourists, a is circumscribed rectangular area, and n is number of tourists in tourist group.
Specifically, at 11:08:21, the average nearest distance of tourists in the G group of the tourist group is 0.6 meter, the circumscribed rectangular area is 65.9 square meters, and the number of tourists is 12, so that the nearest neighbor index of the tourists is 0.51. Similarly, the nearest neighbor index of tourists in the group G at each moment is calculated separately.
S44: if the nearest neighbor index is smaller than 1 at a certain moment, the tourist group is in a distributed formation at the moment.
Specifically, if the nearest neighbor index of tourists in the tourist group G is 0.51 at 11:08:21, the tourist group G is a distributed formation at 11:08:21, as shown in FIG. 4.
S45: if the ratio of tourists with the changed coordinates is smaller than the preset ratio threshold value, the tourists with the tourists group at the moment are at rest, otherwise, the tourists with the tourists group at the moment are shopping.
Specifically, compared with 11:08:20, at 11:08:21, the tourist group G has 1 tourist with changed coordinates, and the tourist ratio with changed coordinates is: 1/12×100% =8.3%. Less than a preset ratio threshold (e.g., 25%), then at 11:08:21, the group G guest is resting. Similarly, at 11:26:58, the tourist group G is a distributed formation, the ratio of tourists with changed coordinates is 58.3%, and the ratio is greater than a preset ratio threshold, and at 11:26:58, the tourist group G tourists are shopping.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. The tourist group tourist behavior identification method is characterized by comprising the following steps:
s1: acquiring trace data of a travel group, and preprocessing to generate trace data of the travel group;
s2: identifying whether the tourist group is a team formation or not according to the tourist group tourist distribution characteristics, if so, further identifying the riding behavior, the walking behavior and the queuing behavior of the tourist group tourist;
s3: according to the distribution characteristics of tourists of the tourists, whether the tourists are round formations or not is identified, and if so, the listening and speaking behaviors and dining behaviors of the tourists are further identified;
s4: and (3) identifying whether the tourist group is a distributed formation according to the distribution characteristics of tourist group tourists, and if so, further identifying the rest behaviors and shopping behaviors of the tourist group tourists.
2. The tourist group behavior recognition method according to claim 1, wherein the group following track in step S1 is formed by a series of tourist track points including tourist group number, tourist number, tour guide sign, time and coordinate information from the processing result of high-precision positioning track data.
3. The tourist group tourist behavior identification method according to claim 1, wherein the preprocessing in step S1 specifically comprises the following steps:
s11: extracting tourist track points with the same tourist group number and marking the tourist track points as tourist group track data;
s12: and calculating the activity speed of the tourist group at each moment according to the barycenter coordinates of the tourist group at each moment and the corresponding previous moment.
4. The tourist group tourist behavior identification method according to claim 1, wherein the specific steps in the step S2 are as follows:
s21: connecting a tourist coordinate in each moment with other tourist coordinates, marking the tourist coordinate as a connecting direction, calculating an included angle and a complementary angle between each connecting direction and other connecting directions, counting the times that the included angle or the complementary angle is smaller than a preset included angle threshold value, marking the times as the included angle, marking the connecting direction corresponding to the maximum included angle times as a longitudinal direction, and marking other tourists of which the included angle or the complementary angle between the connecting direction and the longitudinal direction is smaller than a preset included angle threshold value as the same longitudinal tourists;
s22: repeating the step S21, and identifying the direction of the tourist and the tourist in the same team except the tourist and the tourist in the same team in each moment;
s23: calculating an included angle and a complementary angle between the longitudinal team directions in the tourist group at each moment;
s24: if the included angle or the complement angle between the longitudinal team directions at a certain moment is smaller than a preset included angle threshold value, the tourist group is a longitudinal team form at the moment;
s25: if the activity speed of the tourist group is greater than the preset walking speed upper limit, the tourist group tourist is in riding behavior at the moment;
s26: if the activity speed of the tourist group is smaller than the upper limit of the preset walking speed and the activity speed of the tourist group is larger than the lower limit of the preset walking speed, the tourist group tourist is walking at the moment;
s27: if the activity speed of the tourist group is smaller than the preset walking speed lower limit, the tourist group tourist is in queuing.
5. The tourist group tourist behavior identification method according to claim 1, wherein the specific steps in the step S3 are as follows:
s31: calculating the sum of the distances between each tourist coordinate and other tourist coordinates in the tourist group at each moment, marking the sum as the total distance among the tourists, counting the average value of the total distances among the tourists, and marking the average total distance among the tourists;
s32: if the total distance between all tourists in the tourist group at a certain moment is larger than the product of the average total distance between the tourists and the lower limit of the ratio of the preset distance and smaller than the product of the average total distance between the tourists and the upper limit of the ratio of the preset distance, the tourist group at the moment is in a round formation;
s33: if the tour guide personnel are positioned in the round formation of the tourist group, the tourist group tourist is in listening and speaking behaviors at the moment, and otherwise, is dining behaviors.
6. The tourist group tourist behavior identification method according to claim 1, wherein the specific steps in the step S4 are as follows:
s41: calculating the nearest distance between each tourist coordinate and other tourist coordinates in each time tourist group, counting the average value of the nearest distances of each tourist, and marking the average nearest distance as the average nearest distance of the tourists;
s42: counting the maximum value and the minimum value of the transverse and longitudinal coordinates of each tourist in each time tourist group, further generating an external rectangle of each tourist coordinate, and calculating the area of the external rectangle;
s43: the nearest neighbor index of tourists in the tourist group at each moment is calculated, and the calculation formula is as follows:
NNI＝D/[0.5×(A/n) 0.5 ]
wherein NNI is nearest neighbor index, D is average nearest distance of tourists, A is external rectangular area, n is number of tourists in tourist group;
s44: if the nearest neighbor index at a certain moment is smaller than 1, the tourist group at the moment is in a distributed formation;
s45: if the ratio of tourists with the changed coordinates is smaller than the preset ratio threshold value, the tourists with the tourists group at the moment are at rest, otherwise, the tourists with the tourists group at the moment are shopping.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311208043.4A CN117372946B (en) | 2023-09-19 | 2023-09-19 | Tourist group tourist behavior identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311208043.4A CN117372946B (en) | 2023-09-19 | 2023-09-19 | Tourist group tourist behavior identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117372946A true CN117372946A (en) | 2024-01-09 |
| CN117372946B CN117372946B (en) | 2024-04-16 |
Family
ID=89401262
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311208043.4A Active CN117372946B (en) | 2023-09-19 | 2023-09-19 | Tourist group tourist behavior identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117372946B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103383461A (en) * | 2013-07-19 | 2013-11-06 | 苏州海客科技有限公司 | Position obtaining method for tourist group |
| CN108269203A (en) * | 2018-02-08 | 2018-07-10 | 湖南三纬码信息技术有限公司 | Tourism belt group's method, tourist group's management system, management of tour guide system, tourist system |
| CN109919624A (en) * | 2019-02-28 | 2019-06-21 | 杭州师范大学 | A kind of net loan fraud clique's identification and method for early warning based on space-time centrality |
| CN110059668A (en) * | 2019-04-29 | 2019-07-26 | 中国民用航空总局第二研究所 | Behavior prediction processing method, device and electronic equipment |
| CN111368650A (en) * | 2020-02-18 | 2020-07-03 | 北京交通大学 | Crowd crowding behavior identification method based on track data |
| CN112330498A (en) * | 2020-10-22 | 2021-02-05 | 马上游科技股份有限公司 | Method and system for carrying out grouping management based on tourist positions |
| CN113535872A (en) * | 2021-07-12 | 2021-10-22 | 中国人民解放军战略支援部队信息工程大学 | Multi-granularity formation motion visualization method based on object |
| CN114429318A (en) * | 2022-04-07 | 2022-05-03 | 环球数科集团有限公司 | Member management method and device for tourist group and computer equipment |
| CN115358621A (en) * | 2022-09-02 | 2022-11-18 | 北京理工大学 | Crowd formation planning method and system based on characteristic anchor points |
| CN116129263A (en) * | 2022-12-30 | 2023-05-16 | 中国人民解放军火箭军工程大学 | Cluster ship formation identification method based on topological structure similarity |
| CN116343133A (en) * | 2023-05-29 | 2023-06-27 | 日照市规划设计研究院集团有限公司 | Tourist group type identification method based on track big data |
| CN116483082A (en) * | 2023-04-20 | 2023-07-25 | 哈尔滨工程大学 | Multi-agent formation recognition method based on interpolation and fuzzy recognition |
| CN116610989A (en) * | 2023-07-19 | 2023-08-18 | 日照市规划设计研究院集团有限公司 | Tourist group type identification method based on group following travel track data |
-
2023
- 2023-09-19 CN CN202311208043.4A patent/CN117372946B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103383461A (en) * | 2013-07-19 | 2013-11-06 | 苏州海客科技有限公司 | Position obtaining method for tourist group |
| CN108269203A (en) * | 2018-02-08 | 2018-07-10 | 湖南三纬码信息技术有限公司 | Tourism belt group's method, tourist group's management system, management of tour guide system, tourist system |
| CN109919624A (en) * | 2019-02-28 | 2019-06-21 | 杭州师范大学 | A kind of net loan fraud clique's identification and method for early warning based on space-time centrality |
| CN110059668A (en) * | 2019-04-29 | 2019-07-26 | 中国民用航空总局第二研究所 | Behavior prediction processing method, device and electronic equipment |
| CN111368650A (en) * | 2020-02-18 | 2020-07-03 | 北京交通大学 | Crowd crowding behavior identification method based on track data |
| CN112330498A (en) * | 2020-10-22 | 2021-02-05 | 马上游科技股份有限公司 | Method and system for carrying out grouping management based on tourist positions |
| CN113535872A (en) * | 2021-07-12 | 2021-10-22 | 中国人民解放军战略支援部队信息工程大学 | Multi-granularity formation motion visualization method based on object |
| CN114429318A (en) * | 2022-04-07 | 2022-05-03 | 环球数科集团有限公司 | Member management method and device for tourist group and computer equipment |
| CN115358621A (en) * | 2022-09-02 | 2022-11-18 | 北京理工大学 | Crowd formation planning method and system based on characteristic anchor points |
| CN116129263A (en) * | 2022-12-30 | 2023-05-16 | 中国人民解放军火箭军工程大学 | Cluster ship formation identification method based on topological structure similarity |
| CN116483082A (en) * | 2023-04-20 | 2023-07-25 | 哈尔滨工程大学 | Multi-agent formation recognition method based on interpolation and fuzzy recognition |
| CN116343133A (en) * | 2023-05-29 | 2023-06-27 | 日照市规划设计研究院集团有限公司 | Tourist group type identification method based on track big data |
| CN116610989A (en) * | 2023-07-19 | 2023-08-18 | 日照市规划设计研究院集团有限公司 | Tourist group type identification method based on group following travel track data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117372946B (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105389332B (en) | It is a kind of geography social networks under user's similarity calculation method | |
| CN104123398B (en) | A kind of information-pushing method and device | |
| CN105872034B (en) | Tracking and system, the method and mobile communications device using it of record motion | |
| CN109359521A (en) | The two-way assessment system of Classroom instruction quality based on deep learning | |
| CN105095242B (en) | A kind of method and apparatus of label geographic area | |
| CN116343133B (en) | Tourist group type identification method based on track big data | |
| JP2003523581A (en) | Method and apparatus for discovering collaboration destination of mobile user | |
| CN107948928A (en) | Expert by rule of thumb determines and problem route system and method | |
| CN107610765A (en) | A kind of human activity is worth monitoring method and system | |
| CN104166663A (en) | Taxi taking position recommending system and method based on multiple dimensions | |
| CN106951903A (en) | A kind of method for visualizing of crowd's movement law | |
| CN107045519B (en) | A kind of visualization system of analysis crowd movement law | |
| CN106341312A (en) | Social contact information display method, system and server | |
| CN109977324A (en) | A kind of point of interest method for digging and system | |
| CN117372946B (en) | Tourist group tourist behavior identification method | |
| Want | An introduction to ubiquitous computing | |
| CN111178643A (en) | Intelligent guide method and system for group sports | |
| CN116610989B (en) | Tourist group type identification method based on group following travel track data | |
| CN112699402B (en) | Wearable device activity prediction method based on federal personalized random forest | |
| CN109949010A (en) | Hospital's high-level personnel's evaluation system of big data based on Information System Integration | |
| CN109308567A (en) | A kind of full dimension service evaluation system of travelling products and method | |
| CN104850657A (en) | Holographic position map superposing method | |
| CN115410720A (en) | Clustered infectious disease epidemic situation early warning method based on confirmed patient trajectory characteristics | |
| CN108737951A (en) | One kind monitoring stream of people's movement track system based on Mobile Location Technology | |
| KR20200091193A (en) | Apparatus and method for automatically analyzing urban areas, station area and hot place through location-based sns data |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |