CN112988936A - Travel track prediction method and device, computing equipment and storage medium - Google Patents
Travel track prediction method and device, computing equipment and storage medium Download PDFInfo
- Publication number
- CN112988936A CN112988936A CN202110292859.4A CN202110292859A CN112988936A CN 112988936 A CN112988936 A CN 112988936A CN 202110292859 A CN202110292859 A CN 202110292859A CN 112988936 A CN112988936 A CN 112988936A
- Authority
- CN
- China
- Prior art keywords
- track
- grid
- travel
- sequence
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 description 12
- 230000000694 effects Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 235000019580 granularity Nutrition 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 230000006855 networking Effects 0.000 description 3
- 239000000523 sample Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90344—Query processing by using string matching techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/909—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- General Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Networks & Wireless Communication (AREA)
- Life Sciences & Earth Sciences (AREA)
- Library & Information Science (AREA)
- Computational Linguistics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a travel track prediction method, a travel track prediction device, a computing device and a storage medium. The method comprises the following steps: acquiring travel data of a vehicle, wherein the travel data comprises longitude data and latitude data; carrying out grid coding on the travel data to obtain a time sequence grid track of the vehicle; calculating the similarity between the time sequence grid track and each track sequence in a track library, wherein the track library comprises at least one track sequence; and predicting the travel track of the vehicle according to the similarity. According to the technical scheme, the travel data are gridded, the existing track sequence in the track library is combined, the vehicle travel track is effectively predicted, and the prediction fineness and accuracy are improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of intelligent travel, in particular to a travel track prediction method, a travel track prediction device, a computing device and a storage medium.
Background
With the increasingly wide application of the GPS technology, data mining and application based on the GPS technology become a new hot spot for intelligent travel. The vehicle-mounted navigation equipment, the mobile phone navigation software and the like can guide the user to travel efficiently according to the destination input by the user and the selected route. Travel scene recognition is more and more important in the application of vehicle intellectualization and personalized service, the requirements on the accuracy and fineness of travel scene recognition are higher and higher, and the method is the key for improving user experience. For example, a private car goes home on holidays and goes to visit a relative or go for a long distance, which is obviously different from the travel track of daily work or life, and therefore the travel track under different scenes can be intelligently identified or predicted. However, under the condition that the user does not input a destination or select a route, a lot of uncertain factors exist, the calculation power of a vehicle end, the summarizing and analyzing capability of multiple data and the like have limitations, the travel track of the vehicle is difficult to be effectively predicted, and the prediction precision and accuracy are low.
Disclosure of Invention
The invention provides a travel track prediction method, a travel track prediction device, a computing device and a storage medium, which are used for effectively predicting a travel track of a vehicle in real time and improving the prediction fineness and accuracy.
In a first aspect, an embodiment of the present invention provides a travel trajectory prediction method, including:
acquiring travel data of a vehicle, wherein the travel data comprises longitude data and latitude data;
carrying out grid coding on the travel data to obtain a time sequence grid track of the vehicle;
calculating the similarity between the time sequence grid track and each track sequence in a track library, wherein the track library comprises at least one track sequence;
and predicting the travel track of the vehicle according to the similarity.
Optionally, the grid encoding the travel data to obtain a time sequence grid track of the vehicle includes:
encoding the longitude data and the latitude data based on an address encoding algorithm to obtain a character string;
merging adjacent grids according to the character strings to obtain the time sequence grid track and the following information of the time sequence grid track: time to enter the grid, time to leave the grid, grid coding, dwell time within the grid, and transit speed.
Optionally, calculating the similarity between the time-series grid trajectory and each trajectory sequence in the trajectory library includes:
and if the number or the proportion of the unconventional active grids in the time sequence grid track reaches a set threshold value, calculating the Levenstein distance between the time sequence grid track and each track sequence in the track library as the corresponding similarity of each track sequence.
Optionally, predicting the travel track of the vehicle according to the similarity includes:
and if the highest similarity in the similarities corresponding to the track sequences is greater than the similarity threshold, taking the track sequence corresponding to the highest similarity as the travel track of the vehicle.
Optionally, the method further includes:
obtaining historical trip data of a vehicle, wherein the historical trip data comprises historical longitude data and historical latitude data;
and carrying out grid coding on the historical trip data to obtain at least one track sequence, and marking a conventional active grid.
Optionally, marking the regular active mesh comprises:
determining grid score according to the stay time in the grid and/or the grid in-and-out frequency;
and selecting a set number of grids with the highest grid score as conventional active grids for the track sequences in the frequently active area.
Optionally, the method further includes:
and determining a destination grid in the track sequence with the highest similarity to the travel track according to the stay time in the grid, and predicting the destination of the travel track according to the destination grid.
In a second aspect, an embodiment of the present invention provides a travel trajectory prediction apparatus, including:
the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring travel data of a vehicle, and the travel data comprises longitude data and latitude data;
the encoding module is used for carrying out grid encoding on the trip data to obtain a time sequence grid track of the vehicle;
the calculation module is used for calculating the similarity between the time sequence grid track and each track sequence in a track library, and the track library comprises at least one track sequence;
and the prediction module is used for predicting the travel track of the vehicle according to the similarity.
In a third aspect, an embodiment of the present invention provides a computing device, including:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a travel trajectory prediction method as described in the first aspect.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the travel trajectory prediction method according to the first aspect.
The embodiment of the invention provides a travel track prediction method, a travel track prediction device, a computing device and a storage medium. The method comprises the following steps: acquiring travel data of a vehicle, wherein the travel data comprises longitude data and latitude data; carrying out grid coding on the travel data to obtain a time sequence grid track of the vehicle; calculating the similarity between the time sequence grid track and each track sequence in a track library, wherein the track library comprises at least one track sequence; and predicting the travel track of the vehicle according to the similarity. According to the technical scheme, the travel data are gridded, the existing track sequence in the track library is combined, the vehicle travel track is effectively predicted, and the prediction fineness and accuracy are improved.
Drawings
Fig. 1 is a flowchart of a travel trajectory prediction method according to an embodiment of the present invention;
fig. 2 is a flowchart of a travel trajectory prediction method according to a second embodiment of the present invention;
fig. 3 is a schematic diagram of a timing grid trace according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of a travel trajectory prediction apparatus according to a third embodiment of the present invention;
fig. 5 is a schematic diagram of a hardware structure of a computing device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. In addition, the embodiments and features of the embodiments in the present invention may be combined with each other without conflict. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the steps as a sequential process, many of the steps can be performed in parallel, concurrently or simultaneously. In addition, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Example one
Fig. 1 is a flowchart of a travel trajectory prediction method according to an embodiment of the present invention, which is applicable to predicting a travel trajectory according to a real-time position of a vehicle, and is particularly applicable to intelligently identifying travel scenes such as long-distance travel, routine trips, hometown visits and the like. Specifically, the travel trajectory prediction method may be executed by a travel trajectory prediction apparatus, which may be implemented by software and/or hardware and integrated in a computing device. Further, computing devices include, but are not limited to: desktop computer, driving computer, smart mobile phone, car networking server and high in the clouds server etc. electronic equipment.
As shown in fig. 1, the method specifically includes the following steps:
s110, obtaining travel data of the vehicle, wherein the travel data comprise longitude data and latitude data.
In this embodiment, the trip data refers to data reflecting the position of the vehicle, such as Global Positioning System (GPS) data, and specifically, longitude data and latitude data may be used to represent the real-time position of the vehicle. Longitude data and latitude data can be extracted from the standard signal of the internet of vehicles which is regularly collected and reported by a vehicle-mounted remote information processor (T-BOX) and are preprocessed to filter invalid values and abnormal values, improve data quality and provide a reliable data basis for subsequent travel track prediction. It can be understood that the travel data may further include time information (timestamps corresponding to longitude data and latitude data), a Vehicle Identification Number (VIN), an altitude, a GPS Vehicle speed, a driving direction, and the like, so as to facilitate analyzing a time sequence characteristic of the travel data, more accurately analyze a Vehicle position, and predict a travel track.
And S120, carrying out grid coding on the travel data to obtain a time sequence grid track of the vehicle.
In this embodiment, the longitude data and the latitude data are subjected to grid coding, and adjacent grids are combined to generate a consecutive time-series grid trajectory. The trellis coding may be multi-level trellis coding, that is, address coding of a trellis string with different granularities for converting longitude and latitude into, so as to achieve the purpose of reducing dimension and improving computational efficiency.
S130, calculating the similarity between the time sequence grid track and each track sequence in a track library, wherein the track library comprises at least one track sequence.
In this embodiment, a track sequence recorded according to the historical travel track of the vehicle is stored in the track library, and is used for summarizing the characteristics and rules of historical travel. By comparing the time sequence grid track obtained by the current trip with each track sequence in the track library, if the similarity between one track sequence and the current time sequence grid track is high enough, the trip track of the vehicle can be predicted according to the track sequence. For example, two sequences of traces are stored in the trace: a-B-C-D-E and a-D-E-F-G, where different letters represent different positions or grids. The time sequence grid track currently obtained by the vehicle trip comprises three grids: A-B-C, it can be seen that the current time sequence grid is consistent with the first three items of the first track sequence, and the first track sequence is likely to be the travel track of the trip. The method for calculating the similarity is not particularly limited in this embodiment.
And S140, predicting the travel track of the vehicle according to the similarity.
Specifically, the trajectory sequence with the highest similarity to the time-series grid trajectory in the trajectory library may be used as a prediction result of the travel trajectory. In addition, after the travel track of the vehicle is predicted, a corresponding backward service decision can be triggered, for example, a gas station, a rest station, a shopping point or a scenic spot in the travel track is intelligently recommended to the vehicle owner, congestion road sections, expected time, weather service and homeward returning information in the travel track are prompted, intelligent voice care interaction is provided, and user experience is improved.
Furthermore, the prediction result can be further optimized by combining the set judgment condition. For example, when the highest similarity between each track sequence in the track library and the time-series grid track reaches a similarity threshold (90%), the track sequence can be determined as the travel track of the vehicle; if the highest similarity does not reach the similarity threshold, the difference between each track sequence in the track library and the current time sequence grid track is large, namely, a track sequence close to the current time sequence grid track is not found in the track library, at the moment, a prediction result cannot be obtained, the travel data can be continuously collected, and the track sequence with high enough similarity can be found in the track library again. By setting a similarity threshold, a certain range of errors between the time sequence grid track and the track sequence are allowed, and accurate prediction can be realized under the condition that the travel and a certain track sequence have the same destination and a section of track which is approximately similar, but the specific travel route is slightly different (for example, the route is adjusted due to congestion avoidance, charge avoidance and the like).
Furthermore, the prediction result can be further optimized by combining the set travel factors. For example, on weekdays and double holidays of non-legal festivals, the travel tracks of the vehicle mainly relate to frequent activity areas, such as the place where the owner resides, the place where the owner works, the shopping mall, the dining room, and the like; on the legal holidays (or on the short or long holidays), the vehicle owner needs to go out for a long distance, for example, returning to the home, the vehicle travel track mainly relates to the hometown of the vehicle owner, and the travel track has certain regularity but does not appear frequently and does not belong to a frequent activity area. In this case, if the trip is in the legal holiday period, the similarity between the current time-series grid trajectory and the trajectory sequence related to the hometown in the trajectory library is higher than the similarity between the current time-series grid trajectory and other trajectory sequences, and the similarity is also higher than the similarity between the current time-series grid trajectory and the trajectory sequence related to the trip scene of the non-legal holiday.
The specific implementation manner of further optimizing the prediction result by combining the set travel factors may be that, in the process of calculating the similarity between the time-series grid trajectory and each trajectory sequence in the trajectory library, the factors of the legal holidays can be considered, and the similarity is optimized and calculated by using the adjustment factors. For example, the trajectory stores a trajectory sequence corresponding to travel of a legal holiday: A-B-C-D-E. The present trip of the vehicle is during the legal holiday, and the currently obtained time sequence grid track comprises three grids: a-F-G, with an adjustment factor of 1.2, the similarity between the current time-series grid and the first trajectory sequence is multiplied by 1.2 based on the original similarity, for example, the original similarity is 33.3% (1/3 in the current time-series grid trajectory is the same as the grid in the first trajectory sequence), and the optimized similarity is 33.3%. 1.2 ≈ 39.9%. For another example, at the end of each month, the vehicle owner needs to go to a long-distance business trip between a non-residential place and a non-working place, in this case, if the trip is at the end of the month, in the process of calculating the similarity between the time sequence grid trajectory and each trajectory sequence in the trajectory library, whether the similarity is the factor at the end of the month or not can be considered, and the similarity is optimally calculated by using the adjustment factor.
According to the travel track prediction method provided by the embodiment of the invention, travel track prediction is realized by collecting and analyzing travel data and combining a track sequence in a track library; by calculating the similarity between the time-sequence grid track and each track sequence in the track library, the prediction precision and accuracy are improved, and the purposes of regularizing travel behaviors and effectively identifying travel scenes without depending on map vector data and road matching can be achieved; and a reliable basis can be provided for intelligent recommendation service.
Example two
Fig. 2 is a flowchart of a travel trajectory prediction method according to a second embodiment of the present invention, which is optimized based on the second embodiment, and specifically describes processes of trellis coding and similarity calculation. It should be noted that technical details that are not described in detail in the present embodiment may be referred to any of the above embodiments.
Specifically, as shown in fig. 2, the method specifically includes the following steps:
s210, obtaining historical travel data of the vehicle, wherein the historical travel data comprises historical longitude data and historical latitude data.
Specifically, the historical travel data is used to reflect the location of the vehicle over a period of time in the past. Historical longitude data and historical latitude data can be extracted from the vehicle networking standard signals collected and reported by the T-BOX, and can be recorded and stored in real time. It can be understood that the historical travel data further includes historical time information, vehicle VIN codes, historical heights, GPS historical vehicle speeds, historical travel directions and the like, so that the time sequence characteristics of the historical travel data can be analyzed conveniently, and the vehicle position and the travel track can be more accurately analyzed.
And S220, carrying out grid coding on the historical trip data to obtain at least one track sequence, and marking a conventional active grid.
In this embodiment, the conventional active grid mainly refers to a grid corresponding to a constant active area of a vehicle during a work day and a double holiday of a non-legal holiday. Taking a scene of hometown exploration as an example, the conventional activity grid can be a grid corresponding to the positions of the owner's residence, workplace, shopping mall, dining room and the like during the weekday and the double holiday of non-legal festivals and holidays. For the current time sequence grid track, if the number of the non-conventional active grids reaches a certain number, the vehicle is out of the normal activity area and enters a track with certain regularity but not frequent, and the travel track prediction can be realized by calculating the similarity under the condition.
In the process of grid coding historical travel data, grid numbers can be used as a unit, on one hand, a conventional active grid is marked, on the other hand, a track sequence of a hometown seeker can be generated based on the historical travel data, a destination is recorded, specifically, the track sequence of the hometown seeker can be obtained by weighting grids of the historical travel data related to the hometown seeker for multiple times, a label is added to the track sequence, the track sequence is stored in a track library, and the track sequence is used for being compared with a time sequence grid track. It should be noted that, as a method for trellis-encoding historical travel data, reference may be made to the method for trellis-encoding current travel data in this embodiment.
Optionally, marking the regular active mesh comprises: determining grid score according to the stay time in the grid and/or the grid in-and-out frequency; and selecting a set number of grids with the highest grid score as conventional active grids for the track sequences in the frequently active area.
Illustratively, for historical trip data, the retention time T in the ith grid is usediThe frequency of the i-th grid is NiSelecting historical trip data with trip time of working days and non-legal holidays as grid scores of the ith grid, and sorting the grid scores to obtain the gridThe grid with the top 90% of the grid values is added into the conventional active grid set C: c ═ TOP Ti}∪{TOP Ni}. Additionally, the trajectory sequence and the conventional activity grid may also be verified and adjusted based on known test data sets (including basic information of the vehicle, such as the owner's residence, workplace, native place, areas of constant activity, etc.).
Optionally, the track sequences in the track library may be divided into different sub-track libraries. For example, a track sequence with the destination of historical travel being the home of the owner and the travel distance exceeding 10km is used as a sub-track library related to the hometown seeker and is specially used for travel track prediction of the hometown seeker.
And S230, obtaining travel data of the vehicle, wherein the travel data comprise longitude data and latitude data.
And S240, encoding the longitude data and the latitude data based on an address encoding algorithm to obtain a character string.
In this embodiment, grid coding is performed based on a longitude and latitude address coding (GeoHash) algorithm, two-dimensional longitude and latitude data are coded into character strings, and corresponding longitude or latitude values are infinitely approximated by a binary method. An example of a process for trellis coding is as follows:
1) setting north latitude as positive and south latitude as negative, numbering by dichotomy in the range of [ -90 degrees and 90 degrees ], converting the latitude falling on the left side of the median point into '0', and converting the latitudes of the median point and the right side into '1'; the east longitude is set to be positive, the west longitude is set to be negative, bisection numbering is carried out in the range of [ -180 degrees, 180 degrees ], the longitude on the left side of the median point is converted into '0', and the longitude on the right side of the median point is converted into '1'.
2) And sequentially interleaving and combining '0' and '1' of the longitude and latitude to obtain a group of preliminary character strings, wherein odd digits are latitude values, and even digits are longitude values.
3) Converting every 5 bits into 10-system numbers, and converting into final character strings by adopting a Base32 encoding mode.
And S250, merging adjacent grids according to the character strings to obtain the time sequence grid track.
Specifically, the encoded character strings are combined according to the encoding lengths of different levels, so that time sequence grid tracks with various accuracies can be obtained, and the accuracies can be embodied by the grid size (width and height). For example, the character strings obtained by grid coding are respectively intercepted according to different coding lengths (6, 7, 8 or 9 bit characters) so as to obtain time sequence grid tracks with different accuracies.
Table 1 is a mapping relationship table between the coding length and the grid size, and as shown in table 1, the smaller the coding length, the smaller the grid size, and the higher the accuracy.
TABLE 1 mapping relationship table of code length and mesh size
| Code length | Number of latitude bits | Number of longitude bits | Error in latitude | Error in longitude | Grid width | Height of grid |
| 6 | 15 | 15 | ±0.0027 | ±0.0055 | 1.2km | 609.4m |
| 7 | 17 | 18 | ±0.00068 | ±0.00068 | 152.9m | 152.4m |
| 8 | 20 | 20 | ±0.000086 | ±0.000172 | 38.2m | 19m |
| 9 | 22 | 23 | ±0.000021 | ±0.000021 | 4.8m | 4.8m |
It should be noted that the trajectory sequence obtained according to the historical trip data may also be divided into different accuracies, so that when the similarity between the current time sequence grid trajectory and each trajectory sequence is calculated, various accuracies are provided, and the method is applicable to different scenes. For example, if the travel distance of the hometown seeker is relatively long, or the number of grids to be compared is relatively large, the partition granularity of the grids is relatively large, and the proportion of local errors is small, a time sequence grid track and a track sequence with low accuracy can be selected to calculate the similarity; the travel distance of the homeward seeking relative is relatively short, or the number of grids needing to be compared is relatively small, the partition granularity of the grids is relatively small, the proportion of local errors is large, and then the time sequence grid track and the track sequence with high accuracy can be selected to calculate the similarity. On the basis, the effect compatibility of different trip data and trip scenes is realized, and the flexibility and the reliability of prediction are improved.
Fig. 3 is a schematic diagram of a timing grid trace according to a second embodiment of the present invention. As shown in fig. 3, grid encoding longitude data and latitude data, and then merging adjacent grids, may result in generating a coherent time-series grid trajectory. The granularity (coding length) of grid division is different, the height and width of the grid are different, and the accuracy of the time sequence grid track is also different.
Further, in the process of grid coding, the following information of the time-sequence grid tracks is obtained: the time of entering the grid, the time of leaving the grid, the grid coding, the stay time in the grid and the passing speed are convenient to analyze the conventional active grid and the unconventional active grid in the current time sequence grid track, the prediction accuracy is improved, and a basis is provided for predicting the travel destination.
S260, does the number or proportion of unconventional active grids in the time-series grid trajectory reach a set threshold? If yes, go to S270; if not, the process returns to the step S230.
In this embodiment, for the current time-series grid trajectory, if the occupancy of the irregular active grid therein reaches a set threshold (for example, 20%, where the threshold is preset according to an empirical value, and may also be adjusted according to the occupancy and distribution of the regular active grid in the trajectory library), it may also be understood that the occupancy of the regular active grid therein is smaller than a corresponding threshold (i.e., 80%), and then the similarity between the current time-series grid trajectory and each trajectory sequence in the trajectory library is calculated and compared. If the conventional activity grid is high in occupation ratio, the travel data are not separated from the frequent activity area of the working day or the double-holiday, prediction is not needed, and the travel data are continuously collected.
S270, calculating the Levensian distance between the time sequence grid track and each track sequence in the track library as the corresponding similarity of each track sequence.
In this embodiment, the similarity is calculated by using the levenstein distance, and the levenstein distance is used for measuring the similarity between two character strings, so that the similarity comparison between grid sequences with different lengths can be satisfied. Regarding a single grid code as a unit, the track sequence can be regarded as a chain-type unit string, and on the basis, similarity calculation can be performed on the current time sequence grid track and each track sequence in the track library. The levenstein distance is expressed as follows:
wherein la,b() Denotes the levenstein distance between the two trellis sequences a, b, i, j respectively denote the lengths of the two trellis sequences.
S280, is the highest similarity greater than the similarity threshold? If yes, go to S290; if not, the process returns to the step S230.
And S290, taking the track sequence corresponding to the highest similarity as the travel track of the vehicle.
In this embodiment, if the highest similarity among the similarities of the current time-series grid trajectory and each trajectory sequence in the trajectory library is greater than the similarity threshold, the current time-series grid trajectory is identified as a trajectory of a back-to-country probe, and the corresponding trajectory sequence is used as a prediction result.
In one embodiment, the method further comprises: and determining a destination grid in the track sequence with the highest similarity to the travel track according to the stay time in the grid, and predicting the destination of the travel track according to the destination grid.
Specifically, a high-frequency destination grid with a long dwell time can be analyzed in combination with a track sequence of legal holidays. For example, a high-frequency destination grid of a non-regular activity area, non-origin city, during a holiday of the day is selected as a destination for a hometown seeker. With dwell time T in the ith gridiAs the evaluation score of the ith grid, the stay time T in each grid is respectively calculated for the track sequence related to the legal holidaysiAnd arranging in reverse order; at the same time, the travel frequency N is related based on a single gridTransWeighting the multiple trips, wherein the final evaluation score F is as follows: f ═ TiNtrans. And selecting the grid with the maximum evaluation score and 8 grids around the grid as destination grids of the track sequence, so as to predict the travel destination on the basis of predicting the travel track.
In addition, the method of the embodiment may also be verified through a known test data set, and the measurement parameter is set based on a confusion matrix and accuracy, where the confusion matrix refers to a sample whose prediction result and true value are both positive (for example, both are tracks of a hometown seeker) and is marked as TP; a sample with a negative prediction result and a negative true value (for example, neither is a trace of a hometown seeker) is recorded as TN; the number of samples with positive prediction results and negative true prediction results is recorded as FP; the number of samples with negative prediction results and positive true values is denoted as TP. The performance of the method can be evaluated by using the precision ratio TP/(TP + FP), the recall ratio TP/(TP + FN), the precision ratio (TP + TN)/(TP + FN + FP + TN), and the like.
The travel track prediction method provided by the second embodiment of the invention is optimized on the basis of the first embodiment, the prediction of the travel track can reach the fine degree of vehicle-mounted intelligent service commercialization, the accuracy is high, the travel track prediction can be realized without depending on map vector data and road matching and the collection and butt joint of data such as navigation and the like, and the application range is wide; by introducing the Levensian distance, the method is suitable for measuring the similarity between long and short track sequences, and improves the accuracy and flexibility of prediction; by establishing the sub-track library in the specific scene, the track library is more targeted, and the prediction accuracy in the specific scene is improved.
EXAMPLE III
Fig. 4 is a schematic structural diagram of a travel trajectory prediction apparatus according to a third embodiment of the present invention. As shown in fig. 4, the travel trajectory prediction apparatus provided in this embodiment includes:
an obtaining module 310, configured to obtain trip data of a vehicle, where the trip data includes longitude data and latitude data;
the encoding module 320 is configured to perform mesh encoding on the travel data to obtain a time sequence mesh track of the vehicle;
a calculating module 330, configured to calculate a similarity between the time-series grid trajectory and each trajectory sequence in a trajectory library, where the trajectory library includes at least one trajectory sequence;
and the predicting module 340 is configured to predict the travel track of the vehicle according to the similarity.
According to the travel track prediction device provided by the third embodiment of the invention, travel data are gridded, and the existing track sequence in the track library is combined, so that the travel track of the vehicle is effectively predicted, and the prediction fineness and accuracy are improved.
On the basis of the above embodiment, the encoding module 320 includes:
the address coding unit is used for coding the longitude data and the latitude data based on an address coding algorithm to obtain a character string;
the grid merging unit is used for merging adjacent grids according to the character strings to obtain the time sequence grid track and the following information of the time sequence grid track: time to enter the grid, time to leave the grid, grid coding, dwell time within the grid, and transit speed.
On the basis of the foregoing embodiment, the calculating module 330 is configured to:
and if the number or the proportion of the unconventional active grids in the time sequence grid track reaches a set threshold value, calculating the Levenstein distance between the time sequence grid track and each track sequence in the track library as the corresponding similarity of each track sequence.
On the basis of the above embodiment, the prediction module 340 is configured to:
and if the highest similarity in the similarities corresponding to the track sequences is greater than the similarity threshold, taking the track sequence corresponding to the highest similarity as the travel track of the vehicle.
On the basis of the above embodiment, the method further includes:
the historical data acquisition module is used for acquiring historical trip data of the vehicle, and the historical trip data comprises historical longitude data and historical latitude data;
and the history coding module is used for carrying out grid coding on the history trip data to obtain at least one track sequence and marking a conventional active grid.
On the basis of the above embodiment, the history encoding module includes:
the scoring unit is used for determining a grid score according to the stay time in the grid and/or the grid entry and exit frequency;
and the marking unit is used for selecting a set number of grids with the highest grid score as the conventional active grids for the track sequences in the frequently active area.
On the basis of the above embodiment, the method further includes:
and the destination prediction module is used for determining a destination mesh in the trajectory sequence with the highest similarity to the travel trajectory according to the stay time in the mesh and predicting the destination of the travel trajectory according to the destination mesh.
The travel trajectory prediction device provided by the third embodiment of the invention can be used for executing the travel trajectory prediction method provided by any of the above embodiments, and has corresponding functions and beneficial effects.
Example four
Fig. 5 is a schematic diagram of a hardware structure of a computing device according to a fourth embodiment of the present invention. Computing devices include, but are not limited to: desktop computer, driving computer, smart mobile phone, car networking server and high in the clouds server etc. electronic equipment. As shown in fig. 5, the computing device provided in the present application includes a memory 42, a processor 41, and a computer program stored on the memory and executable on the processor, and when the processor 41 executes the computer program, the travel trajectory prediction method described above is implemented.
The computing device may also include memory 42; the processor 41 in the computing device may be one or more, and one processor 41 is taken as an example in fig. 5; the memory 42 is used to store one or more programs; the one or more programs are executed by the one or more processors 41, so that the one or more processors 41 implement the travel trajectory prediction method as described in the embodiments of the present application.
The computing device further includes: a communication device 43, an input device 44 and an output device 45.
The processor 41, the memory 42, the communication means 43, the input means 44 and the output means 45 in the computing device may be connected by a bus or other means, as exemplified by the bus connection in fig. 5.
The input device 44 may be used to receive entered numeric or character information and to generate key signal inputs relating to user settings and function controls of the computing device. The output device 45 may include a display device such as a display screen.
The communication means 43 may comprise a receiver and a transmitter. The communication device 43 is configured to perform information transmission and reception communication in accordance with control of the processor 41.
The memory 42, as a computer-readable storage medium, may be configured to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the travel trajectory prediction method according to the embodiment of the present application (for example, the obtaining module 310, the encoding module 320, the calculating module 330, and the predicting module 340 in the travel trajectory prediction apparatus). The memory 42 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the computing device, and the like. Further, the memory 42 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 42 may further include memory located remotely from processor 41, which may be connected to a computing device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
On the basis of the above-mentioned embodiments, the present embodiment further provides a computer-readable storage medium, on which a computer program is stored, the program, when being executed by a travel trajectory prediction apparatus, implementing a travel trajectory prediction method in any of the above-mentioned embodiments of the present invention, the method including: acquiring travel data of a vehicle, wherein the travel data comprises longitude data and latitude data; carrying out grid coding on the travel data to obtain a time sequence grid track of the vehicle; calculating the similarity between the time sequence grid track and each track sequence in a track library, wherein the track library comprises at least one track sequence; and predicting the travel track of the vehicle according to the similarity.
Embodiments of the present invention provide a storage medium including computer-executable instructions, which may take any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer-readable storage medium may be, for example, but is not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM), a flash Memory, an optical fiber, a portable CD-ROM, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. A computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take a variety of forms, including, but not limited to: an electromagnetic signal, an optical signal, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, Radio Frequency (RF), etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the travel trajectory prediction method according to the embodiments of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A travel trajectory prediction method is characterized by comprising the following steps:
acquiring travel data of a vehicle, wherein the travel data comprises longitude data and latitude data;
carrying out grid coding on the travel data to obtain a time sequence grid track of the vehicle;
calculating the similarity between the time sequence grid track and each track sequence in a track library, wherein the track library comprises at least one track sequence;
and predicting the travel track of the vehicle according to the similarity.
2. The method of claim 1, wherein said trellis encoding said travel data to obtain a time-series trellis trace of said vehicle comprises:
encoding the longitude data and the latitude data based on an address encoding algorithm to obtain a character string;
merging adjacent grids according to the character strings to obtain the time sequence grid track and the following information of the time sequence grid track: time to enter the grid, time to leave the grid, grid coding, dwell time within the grid, and transit speed.
3. The method of claim 1, wherein calculating the similarity of the time-series grid trajectory to each sequence of trajectories in a trajectory library comprises:
and if the number or the proportion of the unconventional active grids in the time sequence grid track reaches a set threshold value, calculating the Levenstein distance between the time sequence grid track and each track sequence in the track library as the corresponding similarity of each track sequence.
4. The method according to claim 1, wherein predicting the travel track of the vehicle according to the similarity comprises:
and if the highest similarity in the similarities corresponding to the track sequences is greater than the similarity threshold, taking the track sequence corresponding to the highest similarity as the travel track of the vehicle.
5. The method of claim 1, further comprising:
obtaining historical trip data of a vehicle, wherein the historical trip data comprises historical longitude data and historical latitude data;
and carrying out grid coding on the historical trip data to obtain at least one track sequence, and marking a conventional active grid.
6. The method of claim 5, wherein tagging a regular active grid comprises:
determining grid score according to the stay time in the grid and/or the grid in-and-out frequency;
and selecting a set number of grids with the highest grid score as conventional active grids for the track sequences in the frequently active area.
7. The method of claim 1, further comprising:
and determining a destination grid in the track sequence with the highest similarity to the travel track according to the stay time in the grid, and predicting the destination of the travel track according to the destination grid.
8. A travel trajectory prediction apparatus, comprising:
the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring travel data of a vehicle, and the travel data comprises longitude data and latitude data;
the encoding module is used for carrying out grid encoding on the trip data to obtain a time sequence grid track of the vehicle;
the calculation module is used for calculating the similarity between the time sequence grid track and each track sequence in a track library, and the track library comprises at least one track sequence;
and the prediction module is used for predicting the travel track of the vehicle according to the similarity.
9. A computing device, comprising:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a travel trajectory prediction method as claimed in any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements a travel trajectory prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110292859.4A CN112988936A (en) | 2021-03-18 | 2021-03-18 | Travel track prediction method and device, computing equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110292859.4A CN112988936A (en) | 2021-03-18 | 2021-03-18 | Travel track prediction method and device, computing equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112988936A true CN112988936A (en) | 2021-06-18 |
Family
ID=76333018
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110292859.4A Pending CN112988936A (en) | 2021-03-18 | 2021-03-18 | Travel track prediction method and device, computing equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112988936A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113536948A (en) * | 2021-06-22 | 2021-10-22 | 武汉理工大学 | Fishing boat fishing behavior recognition method and device |
| CN113657340A (en) * | 2021-08-26 | 2021-11-16 | 重庆紫光华山智安科技有限公司 | Track matching method and related device |
| CN113806465A (en) * | 2021-09-22 | 2021-12-17 | 公安部交通管理科学研究所 | Bayonet position longitude and latitude deviation correction method based on new energy automobile track data |
| CN113836661A (en) * | 2021-09-24 | 2021-12-24 | 北京百度网讯科技有限公司 | Time prediction method, model training method, related device and electronic equipment |
| CN115966095A (en) * | 2022-12-02 | 2023-04-14 | 云控智行科技有限公司 | Traffic data fusion processing method, device, equipment and medium based on vehicle |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170353941A1 (en) * | 2016-06-07 | 2017-12-07 | NinthDecimal, Inc. | Systems and Methods of Tracking Locations Visited by Mobile Devices to Quantify a Change from a Time Series of Responses |
| CN108153867A (en) * | 2017-12-25 | 2018-06-12 | 山东大学 | User trajectory Forecasting Methodology and device based on temporal regularity |
| CN109496288A (en) * | 2017-07-13 | 2019-03-19 | 北京嘀嘀无限科技发展有限公司 | System and method for determining track |
| CN110516888A (en) * | 2019-09-02 | 2019-11-29 | 重庆紫光华山智安科技有限公司 | Trajectory predictions method, apparatus, electronic equipment and computer readable storage medium |
| CN111402580A (en) * | 2020-03-04 | 2020-07-10 | 杭州海康威视系统技术有限公司 | Vehicle running track prediction method and device and electronic equipment |
-
2021
- 2021-03-18 CN CN202110292859.4A patent/CN112988936A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170353941A1 (en) * | 2016-06-07 | 2017-12-07 | NinthDecimal, Inc. | Systems and Methods of Tracking Locations Visited by Mobile Devices to Quantify a Change from a Time Series of Responses |
| CN109496288A (en) * | 2017-07-13 | 2019-03-19 | 北京嘀嘀无限科技发展有限公司 | System and method for determining track |
| CN108153867A (en) * | 2017-12-25 | 2018-06-12 | 山东大学 | User trajectory Forecasting Methodology and device based on temporal regularity |
| CN110516888A (en) * | 2019-09-02 | 2019-11-29 | 重庆紫光华山智安科技有限公司 | Trajectory predictions method, apparatus, electronic equipment and computer readable storage medium |
| CN111402580A (en) * | 2020-03-04 | 2020-07-10 | 杭州海康威视系统技术有限公司 | Vehicle running track prediction method and device and electronic equipment |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113536948A (en) * | 2021-06-22 | 2021-10-22 | 武汉理工大学 | Fishing boat fishing behavior recognition method and device |
| CN113657340A (en) * | 2021-08-26 | 2021-11-16 | 重庆紫光华山智安科技有限公司 | Track matching method and related device |
| CN113657340B (en) * | 2021-08-26 | 2023-09-05 | 重庆紫光华山智安科技有限公司 | Track matching method and related device |
| CN113806465A (en) * | 2021-09-22 | 2021-12-17 | 公安部交通管理科学研究所 | Bayonet position longitude and latitude deviation correction method based on new energy automobile track data |
| CN113836661A (en) * | 2021-09-24 | 2021-12-24 | 北京百度网讯科技有限公司 | Time prediction method, model training method, related device and electronic equipment |
| CN113836661B (en) * | 2021-09-24 | 2024-02-20 | 北京百度网讯科技有限公司 | Time prediction method, model training method, related device and electronic equipment |
| CN115966095A (en) * | 2022-12-02 | 2023-04-14 | 云控智行科技有限公司 | Traffic data fusion processing method, device, equipment and medium based on vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112988936A (en) | Travel track prediction method and device, computing equipment and storage medium | |
| CN106875066B (en) | Vehicle travel behavior prediction method, device, server and storage medium | |
| CN108320501B (en) | Bus route identification method based on user mobile phone signaling | |
| Mohamed et al. | Accurate real-time map matching for challenging environments | |
| CN103177575B (en) | System and method for dynamically optimizing online dispatching of urban taxies | |
| CN109766777B (en) | Abnormal track detection method and device, storage medium and electronic equipment | |
| CN109033011B (en) | Method and device for calculating track frequency, storage medium and electronic equipment | |
| CN112015835B (en) | Geohash compressed map matching method | |
| CN111985710A (en) | Bus passenger trip station prediction method, storage medium and server | |
| US20190329788A1 (en) | Road condition status prediction method, device, and server, and storage medium | |
| CN110836675B (en) | Decision tree-based automatic driving search decision method | |
| CN103533501A (en) | Geofence generating method | |
| CN103295414A (en) | Bus arrival time forecasting method based on mass historical GPS (global position system) trajectory data | |
| CN110807552B (en) | Urban electric bus driving condition construction method based on improved K-means | |
| CN105120433A (en) | WLAN indoor positioning method based on continuous sampling and fuzzy clustering | |
| CN112344947B (en) | Map matching method, map matching device, electronic equipment and computer readable storage medium | |
| CN110553658B (en) | Navigation path recommendation method, navigation server, computer device and readable medium | |
| CN111737377B (en) | Method and device for identifying drift trajectory, computing equipment and storage medium | |
| Cesario et al. | An approach for the discovery and validation of urban mobility patterns | |
| US20210088350A1 (en) | Systems and methods for determining link topology relationships | |
| Qian et al. | Detecting taxi trajectory anomaly based on spatio-temporal relations | |
| CN109800903A (en) | A kind of profit route planning method based on taxi track data | |
| CN116129643A (en) | Bus travel characteristic identification method, device, equipment and medium | |
| Dalla Torre et al. | A map-matching algorithm dealing with sparse cellular fingerprint observations | |
| EP4092546A1 (en) | Method and apparatus for map query and electronic device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210618 |
|
| RJ01 | Rejection of invention patent application after publication |