Sea surface formation target intention identification method and system

Abstract

The invention relates to the technical field of target intention recognition, and provides a sea surface formation target intention recognition method and system, and the method comprises the steps: obtaining the trajectory data of a sea surface formation target; performing trajectory data preprocessing on the sea surface formation target trajectory data; aiming at the sea surface formation target trajectory data after trajectory data preprocessing, utilizing formation knowledge, position knowledge and route knowledge in a sea surface formation target intention identification knowledge base to respectively construct formation intention identification evidence, position intention identification evidence and route intention identification evidence; and performing comprehensive identification on the formation intention identification evidence, the formation position intention identification evidence and the air route intention identification evidence to generate an intention identification result of the sea surface formation target. The intention recognition speed is high, the robustness is high, and the correct intention recognition rate can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of target intention recognition, and in particular, to a method and system for recognizing the intention of a sea formation target. Background Art

[0002] For the intention recognition of sea formation targets, traditional recognition methods mainly utilize radiation source parameter features such as frequency points, code rates, bandwidths, modulation methods, and the on / off status of means. These features are difficult to obtain, and if the target means is turned off, they cannot be obtained. Currently, many new methods recognize target intentions based on non-radiation source parameters such as the trajectories of formation targets, making up for the loopholes in radiation source parameter recognition. In the prior art: mainly use the target trajectory to recognize the formation shape, believing that the formation shape is strongly correlated with the formation intention, and knowing the formation shape means knowing the formation intention. However, in practical applications, due to the missing phenomenon of formation targets and the missed detection phenomenon of trajectory data, the correct recognition rate is not high; at the same time, due to the dense trajectory points of formation targets and the large number of trajectory points, it takes time to use the formation shape for recognition. There is an urgent need to study a new method for recognizing formation intentions based on trajectories. In addition to using the knowledge of sea formation shapes, add the knowledge of formation positions and formation routes to recognize target intentions, and use the improved evidence theory to fuse the recognition results of formation shapes, positions, and routes to improve the recognition accuracy. At the same time, use the trajectory compression method to reduce the number of trajectory calculation points and improve the recognition efficiency. Summary of the Invention

[0003] The present invention aims to provide a method and system for recognizing the intention of a sea formation target to solve the problems of low recognition accuracy, time-consuming recognition, and insufficient utilization of trajectories existing in the prior art.

[0004] A method for recognizing the intention of a sea formation target provided by the present invention includes:

[0005] Obtain the trajectory data of the sea formation target;

[0006] Perform preprocessing on the trajectory data of the sea formation target;

[0007] For the trajectory data of the sea formation target after preprocessing of the trajectory data, use the formation shape knowledge, position knowledge, and route knowledge in the knowledge base for recognizing the intention of the sea formation target to respectively construct formation intention recognition evidence, position intention recognition evidence, and route intention recognition evidence;

[0008] Perform comprehensive recognition on the formation intention recognition evidence, position intention recognition evidence, and route intention recognition evidence to generate an intention recognition result of the sea formation target.

[0009] In some embodiments, the preprocessing of the trajectory data includes:

[0010] Save the trajectory points classified by the target number, and classify the trajectory points with the same target number into the same category;

[0011] For the same category of trajectories, eliminate illegal values and remove the illegal values from the trajectories;

[0012] Perform trajectory compression and alignment on the same category of trajectories, compress the trajectories and align them to the same time position.

[0013] In some embodiments, the method of saving the trajectory points classified by the target number and classifying the trajectory points with the same target number into the same category is as follows: Arrange the trajectory points with the same target number in ascending order of time and save them into the same linked list in sequence. The one with a smaller time is at the head of the linked list, and the one with a larger time is at the tail of the linked list.

[0014] In some embodiments, the method of eliminating illegal values is as follows: Calculate the trajectory speed of the trajectories in the same linked list in sequence from the second trajectory point at the head to the last trajectory point at the tail. If the trajectory speed of this trajectory point is greater than the preset speed threshold, then this trajectory point is an illegal value, and this trajectory point is removed from the linked list.

[0015] In some embodiments, the method of calculating the trajectory speed is as follows: Divide the Euclidean distance between this trajectory point and the previous trajectory point by the time difference between this trajectory point and the previous trajectory point, and the trajectory speed is obtained.

[0016] In some embodiments, performing trajectory compression and alignment on the same category of trajectories includes:

[0017] Segment the trajectory points according to the time period, and classify the trajectory points with the same target number belonging to the same period into the same segment;

[0018] Perform trajectory compression and alignment on the same segment of trajectories, and compress the trajectory points in the same segment into one trajectory point.

[0019] In some embodiments, segmenting the trajectory points according to the time period includes:

[0020] Find the minimum time and the maximum time of all trajectory points;

[0021] Based on the minimum time, the maximum time, and the preset time period for compression and alignment, calculate the number of segments after segmentation;

[0022] Based on the minimum time and the preset time period for compression and alignment, calculate the intermediate time of each segment.

[0023] In some embodiments, performing trajectory compression and alignment on the same segment of trajectories includes:

[0024] Traverse the intermediate time of each segment, and find the trajectory points belonging to the same segment as the segment where the intermediate time is located in the same trajectory according to the time.

[0025] For the found trajectory points, find two trajectory points with the smallest time difference from the intermediate time. If the number of trajectory points in a certain segment is less than 2, this segment is not compressed. Otherwise, for the two found trajectory points and the intermediate time, use the two-point interpolation formula to calculate the trajectory points after compression and alignment.

[0026] In some embodiments, constructing formation intention recognition evidence includes:

[0027] Obtain the trajectory data of a sea formation target to be recognized after preprocessing the trajectory data;

[0028] For the trajectory data of the sea formation target, traverse the formation knowledge in the sea formation target intention recognition knowledge base, and calculate the formation matching membership degree according to the positions of the formation members in the trajectory data and the formation knowledge;

[0029] Calculate the formation intention recognition evidence according to the formation matching membership degree.

[0030] In some embodiments, constructing position intention recognition evidence includes:

[0031] Obtain the trajectory data of a sea formation target to be recognized after preprocessing the trajectory data;

[0032] For the trajectory data of the sea formation target, traverse the position knowledge in the sea formation target intention recognition knowledge base, and calculate the position matching membership degree according to the positions of the formation members in the trajectory data and the position knowledge;

[0033] Calculate the position intention recognition evidence according to the position matching membership degree.

[0034] In some embodiments, constructing route intention recognition evidence includes:

[0035] Obtain the trajectory data of a sea formation target to be recognized after preprocessing the trajectory data;

[0036] For the trajectory data of the sea formation target, traverse the route knowledge in the sea formation target intention recognition knowledge base, and calculate the route matching membership degree according to the trajectories of the formation members in the trajectory data and the route knowledge;

[0037] Calculate the route intention recognition evidence according to the route matching membership degree.

[0038] In a second aspect, the present invention provides a sea formation target intention recognition system, including:

[0039] A data acquisition module for obtaining the trajectory data of the sea formation target;

[0040] A trajectory data processing module for preprocessing the trajectory data of the sea formation target;

[0041] The formation intention recognition module is used to construct formation intention recognition evidence for the sea formation target trajectory data after trajectory data preprocessing by using the formation knowledge in the sea formation target intention recognition knowledge base.

[0042] The position intention recognition module is used to construct position intention recognition evidence for the sea formation target trajectory data after trajectory data preprocessing by using the position knowledge in the sea formation target intention recognition knowledge base.

[0043] The route intention recognition module is used to construct route intention recognition evidence for the sea formation target trajectory data after trajectory data preprocessing by using the route knowledge in the sea formation target intention recognition knowledge base.

[0044] The intention comprehensive recognition module is used to comprehensively recognize the formation intention recognition evidence, position intention recognition evidence and route intention recognition evidence, and generate an intention recognition result of the sea formation target.

[0045] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are as follows:

[0046] 1. After obtaining the sea formation target trajectory data, the present invention performs trajectory data preprocessing on the trajectory data, segments the trajectory data, reduces the number of trajectory data processed, and improves the intention recognition processing speed.

[0047] 2. The present invention uses formation intention recognition, position intention recognition, and route intention recognition to respectively perform intention recognition on the formation, position, and route of the formation, improving the robustness of intention recognition.

[0048] 3. The present invention uses the improved evidence synthesis theory to fuse the formation intention recognition result, position intention recognition result, and route intention recognition result, improving the recognition accuracy. Description of the Drawings

[0049] Figure 1 is a flowchart of a method for recognizing the intention of a sea formation target provided by an embodiment of the present invention.

[0050] Figure 2 is a flowchart of trajectory data preprocessing in a method for recognizing the intention of a sea formation target provided by an embodiment of the present invention.

[0051] Figure 3 is a flowchart of constructing formation intention recognition evidence in a method for recognizing the intention of a sea formation target provided by an embodiment of the present invention.

[0052] Figure 4 is a flowchart of constructing position intention recognition evidence in a method for recognizing the intention of a sea formation target provided by an embodiment of the present invention.

[0053] Figure 5 It is a flowchart for constructing evidence for route intention recognition in a method for identifying the intention of a sea formation target provided by an embodiment of the present invention.

[0054] Figure 6 It is a flowchart for comprehensive intention recognition in a method for identifying the intention of a sea formation target provided by an embodiment of the present invention.

[0055] Figure 7 It is a schematic structural diagram of a system for identifying the intention of a sea formation target provided by an embodiment of the present invention.

[0056] Figure 8 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0057] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations.

[0058] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0059] Embodiment

[0060] As Figures 1 to 6 shown, to solve the problems of low accuracy and inefficiency in identifying the intention of a sea formation target, the present invention provides a recognition method for identifying the intention of a formation target with fast recognition speed, strong robustness, and significantly improved correct intention recognition rate by using formation trajectory.

[0061] Refer to Figure 1 . To achieve the above objective, the present invention proposes a method for identifying the intention of a sea formation target, including the following steps:

[0062] Obtain the trajectory data of the sea formation target;

[0063] Perform preprocessing on the trajectory data of the sea formation target;

[0064] For the sea formation target trajectory data after preprocessing of trajectory data, using the formation knowledge, position knowledge, and route knowledge in the sea formation target intention recognition knowledge base, construct formation intention recognition evidence, position intention recognition evidence, and route intention recognition evidence respectively;

[0065] Perform comprehensive recognition on the formation intention recognition evidence, position intention recognition evidence, and route intention recognition evidence to generate the intention recognition result of the sea formation target.

[0066] In some embodiments, some definitions in the above method are as follows:

[0067] Trajectory point: It mainly includes the point track of target number, target name, time, rectangular coordinate x1, rectangular coordinate y1, rectangular coordinate z1, spherical coordinate distance r1, spherical coordinate azimuth a1, and spherical coordinate height h1. The spherical coordinate is the position of the member target relative to the main target. The spherical coordinate distance r1 is the distance between the member target and the main target. The spherical coordinate azimuth a1 is the azimuth angle of the member target deviating from the main target's route. The spherical coordinate height h1 is the height of the member target;

[0068] Trajectory: A trajectory formed by arranging all trajectory points with the same target number in ascending order of time;

[0069] Sea formation target: Composed of a sea main target and at least one sea or air member target other than the main target, that is, the sea formation target includes at least two member targets. Let the number of member targets of the sea formation target be n, n≥2;

[0070] Sea formation target trajectory data: Composed of the trajectories of all members of the sea formation target. Each member has one trajectory. The number of sea formation target trajectories is the same as the number of members, that is, the number of trajectories is the number of members n;

[0071] Formation knowledge: It mainly includes the sea formation name, intention name O, target number, target name, rectangular coordinate x2, rectangular coordinate y2, rectangular coordinate z2, spherical coordinate distance r2, spherical coordinate azimuth a2, and spherical coordinate height h2. The spherical coordinate is the spherical coordinate of the member target relative to the main target. The spherical coordinate distance r2 is the distance between the member target and the main target. The spherical coordinate azimuth a2 is the azimuth angle of the member target deviating from the main target's route. The spherical coordinate height h2 is the height of the member target;

[0072] Position knowledge: It mainly includes the sea formation name, intention name O, position number, position radius r3, rectangular coordinates x3, y3, z3 of the position center;

[0073] Route knowledge: It mainly includes the sea formation name, intention name O, target number, trajectory point serial number, rectangular coordinates x4, y4, z4 of the trajectory point;

[0074] Knowledge base for intention recognition of sea formation targets: Each piece of knowledge for intention recognition of sea formation targets includes at least one piece of intention recognition knowledge, which is formation knowledge or position knowledge or route knowledge. Suppose there are m sea formations in the knowledge base for intention recognition of sea formation targets, and each formation of each sea formation has m j members, where j = 1, 2,..., m.

[0075] Refer to Figure 2 . The processing flow of the above-mentioned trajectory data preprocessing is as follows:

[0076] Classify and save trajectory points according to the target number, and classify the trajectory points with the same target number into the same category;

[0077] For the same category of trajectories, eliminate illegal values and remove the illegal values in the trajectories;

[0078] Compress and align the same category of trajectories, compress the trajectories and align them to the same time position.

[0079] In the above-mentioned processing flow of trajectory data preprocessing, the method of classifying and saving trajectory points according to the target number and classifying the trajectory points with the same target number into the same category is: Arrange the trajectory points with the same target number in ascending order of time and save them to the same linked list in sequence, with the one with smaller time at the head of the linked list and the one with larger time at the tail of the linked list.

[0080] In the above-mentioned processing flow of trajectory data preprocessing, the method of eliminating illegal values is: Calculate the trajectory speed v i sequentially from the second trajectory point from the head to the last trajectory point at the tail in the same linked list. If the trajectory speed of this trajectory point is greater than the preset speed threshold (which can be set according to experience and actual needs, for example, set to 20 m / s), then this trajectory point is an illegal value, and this trajectory point is removed from the linked list.

[0081] In the above method of eliminating illegal values, the method of calculating the trajectory speed is: Use the Euclidean distance d i between this trajectory point and the previous trajectory point divided by the time difference t i between this trajectory point and the previous trajectory point, and the trajectory speed v i is obtained. The calculation formula is expressed as v i = d i / t i ;

[0082] In the above-mentioned processing flow of trajectory data preprocessing, the processing flow of compressing and aligning the same category of trajectories is:

[0083] Segment the trajectory points according to the time period, and classify the trajectory points with the same target number belonging to the same period into the same segment;

[0084] For the same trajectory, perform trajectory compression alignment to compress the trajectory points of the same segment into one trajectory point.

[0085] In the above processing flow of trajectory compression alignment for the same type of trajectory, the processing flow of segmenting trajectory points according to a time period is as follows:

[0086] Find the minimum time tMin and the maximum time tMax of all trajectory points;

[0087] Calculate the number of segments after segmentation where tC is the preset time period for compression alignment (which can be set according to experience and actual needs, for example, set to 300 seconds), represents rounding down, such as

[0088] Calculate the intermediate time tn of each segment i = tMin + (i - 0.5) * tC, i = 1, 2,..., n1.

[0089] In the above processing flow of trajectory compression alignment for the same type of trajectory, the processing flow of trajectory compression alignment for the same segment of trajectory is as follows:

[0090] Traverse the intermediate time tn of each segment i , and find the trajectory points in the same trajectory that belong to the same segment as the segment where the intermediate time tn i is located according to time;

[0091] For the found trajectory points, find the two trajectory points with the smallest time difference from the intermediate time tn i . If the number of trajectory points in a certain segment is less than 2, then this segment is not compressed. Otherwise, for the two found trajectory points and the intermediate time tn i , use the two-point interpolation formula to calculate the trajectory point after compression alignment.

[0092] The two-point interpolation formula is expressed as: s = s1 + (s2 - s1) / (t2 - t1) * (t - t1), where (t1, s1) and (t2, s2) are the time and corresponding values of the two input trajectory points, t is the time of the trajectory point after compression alignment, and s is the value of the trajectory point after compression alignment;

[0093] The time of the trajectory point after the above compression alignment is the intermediate time tn i , and the corresponding values of the trajectory points after compression alignment include:

[0094] Position coordinate x1 i = p1.x + (p2.x - p1.x) / (p2.t - p1.t) * (tn i - p1.t), y1i = p1.y + (p2.y - p1.y) / (p2.t - p1.t) * (tn i - p1.t), z1 i = p1.z + (p2.z - p1.z) / (p2.t - p1.t) * (tn i - p1.t);

[0095] Azimuth a1 i = p1.a + (p2.a - p1.a) / (p2.t - p1.t) * (tn i - p1.t);

[0096] Distance r1 i = p1.r + (p2.r - p1.r) / (p2.t - p1.t) * (tn i - p1.t);

[0097] Height h1 i = p1.h + (p2.h - p1.h) / (p2.t - p1.t) * (tn i - p1.t);

[0098] Wherein, p1 and p2 are two trajectory points found. p1.t, p1.x, p1.y, p1.z are the time, position coordinates x, position coordinates y, and position coordinates z of the trajectory point p1 respectively. p1.r, p1.a, p1.h are the distance coordinate r, azimuth coordinate a, and height coordinate h of the spherical coordinates of the trajectory point p1 respectively. p2.t, p2.x, p2.y, p2.z are the time, position coordinates x, position coordinates y, and position coordinates z of the trajectory point p2 respectively. p2.r, p2.a, p2.h are the distance coordinate r, azimuth coordinate a, and height coordinate h of the spherical coordinates of the trajectory point p2 respectively.

[0099] Refer to Figure 3 . The processing flow of the above-mentioned constructed formation intention recognition evidence is as follows:

[0100] Obtain a sea formation target trajectory data to be recognized after preprocessing of trajectory data;

[0101] For the sea formation target trajectory data, traverse the formation knowledge in the sea formation target intention recognition knowledge base, and calculate the formation matching membership degree according to the positions of the formation members in the trajectory data and the formation knowledge;

[0102] Calculate the formation intention recognition evidence according to the formation matching membership degree.

[0103] In the above-mentioned processing flow of constructing formation intention recognition evidence, the calculation formula for calculating the formation matching membership degree according to the positions of the formation members in the trajectory data and the formation knowledge is as follows:

[0104] p1(O j ) = min{max{p1 ik (O j )|i = 1, 2, ..., n}|k = 1, 2, .., m j},

[0105] p1 ik (O j ) = min{p1 rik (O j ), p1 aik (O j ), p1 hik (O j ),

[0106]

[0107]

[0108] Among them, p1(O j ) represents the formation matching membership degree between the trajectory data and the j-th formation knowledge, O j represents the intention name in the j-th formation knowledge, p1 ik (O j ) represents the formation matching membership degree between the i-th member in the trajectory data and the k-th member in the j-th formation knowledge, n represents the number of formation members in the trajectory data, m j represents the number of formation members in the j-th formation knowledge, p1 rik (O j ) represents the distance matching membership degree between the i-th member in the trajectory data and the k-th member in the j-th formation knowledge, p1 aik (O j ) represents the azimuth angle matching membership degree between the i-th member in the trajectory data and the k-th member in the j-th formation knowledge, p1 hik (O j ) represents the height matching membership degree between the i-th member in the trajectory data and the k-th member in the j-th formation knowledge, r1 i is the distance coordinate of the i-th formation member in the trajectory data, a1 i is the azimuth coordinate of the i-th formation member in the trajectory data, h1 i is the height coordinate of the i-th formation member in the trajectory data, r2 jk is the distance coordinate of the k-th formation member in the j-th formation knowledge, a2 jk is the azimuth coordinate of the k-th formation member in the j-th formation knowledge, h2 jkis the height coordinate of the k-th formation member in the j-th formation knowledge, min represents taking the minimum value, and max represents taking the maximum value.

[0109] In the above processing flow for constructing formation intention recognition evidence, the calculation formula for calculating formation intention recognition evidence based on formation matching membership degree is as follows:

[0110]

[0111] p1(Ω) = 1 - max{p1(O j )|j = 1, 2,.., m},

[0112] where p1(O j ) represents the formation matching membership degree between the trajectory data and the j-th formation knowledge, O j represents the intention name in the j-th formation knowledge, Ω represents the uncertainty of the intention, p1(Ω) represents the uncertainty degree of the formation intention recognition evidence, and m is the number of knowledge items.

[0113] Refer to Figure 4 . The processing flow for constructing position intention recognition evidence is as follows:

[0114] Obtain a sea formation target trajectory data to be recognized after preprocessing of the trajectory data;

[0115] For this sea formation target trajectory data, traverse the position knowledge in the sea formation target intention recognition knowledge base, and calculate the position matching membership degree according to the positions of the formation members in the trajectory data and the position knowledge;

[0116] Calculate the position intention recognition evidence according to the position matching membership degree.

[0117] In the above processing flow for constructing position intention recognition evidence, the calculation formula for calculating the position matching membership degree according to the positions of the formation members in the trajectory data and the position knowledge is as follows:

[0118] p2(O j ) = max{max{p2 ik (O j )|i = 1, 2,..., n}|k = 1, 2,.., m j},

[0119]

[0120] where p2(O j ) represents the position matching membership degree between the trajectory data and the j-th position knowledge, O j represents the intention name in the j-th position knowledge, p2 ik (O j) represents the membership degree of the i-th member in the trajectory data to the k-th position in the j-th position knowledge, n represents the number of formation members in the trajectory data, m j represents the number of positions in the j-th position knowledge, r2 jk represents the position radius of the k-th position in the j-th position knowledge, r2 ijk represents the Euclidean distance between the position of the i-th member in the trajectory data and the k-th position in the j-th position knowledge, x1 i is the x coordinate of the i-th formation member in the trajectory data, y1 i is the y coordinate of the i-th formation member in the trajectory data, z1 i is the z coordinate of the i-th formation member in the trajectory data, x3 jk is the x coordinate of the k-th position in the j-th position knowledge, y3 jk is the y coordinate of the k-th position in the j-th position knowledge, z3 jk is the z coordinate of the k-th position in the j-th position knowledge, max represents taking the maximum value.

[0121] In the above processing flow of constructing position intention recognition evidence, the calculation formula for calculating position intention recognition evidence based on the position matching membership degree is as follows:

[0122]

[0123] p2(Ω) = 1 - max{p2(O j )|j = 1, 2,.., m},

[0124] where p2(O j ) represents the membership degree of the trajectory data to the position of the j-th intention knowledge, O j represents the intention name in the j-th intention knowledge, Ω represents the uncertainty of the intention, p2(Ω) represents the uncertainty of the position intention recognition evidence, and m is the number of knowledge items.

[0125] Refer to Figure 5 . The above processing flow of constructing route intention recognition evidence is as follows:

[0126] Obtain a sea formation target trajectory data to be recognized after preprocessing the trajectory data;

[0127] For this sea formation target trajectory data, traverse the route knowledge in the sea formation target intention recognition knowledge base, and calculate the route matching membership degree according to the trajectory of the formation members in the trajectory data and the route knowledge;

[0128] Calculate the route intention recognition evidence according to the route matching membership degree.

[0129] In the above processing flow of constructing evidence for route intention recognition, the calculation formula for calculating the route matching membership degree based on the trajectory data of formation members and route knowledge is as follows:

[0130] p3(O j ) = max{max{p3 ik (O j )|i = 1, 2,..., n}|k = 1, 2,.., m j},

[0131]

[0132] where p3(O j ) represents the route matching membership degree between the trajectory data and the j-th route knowledge, O j represents the intention name in the j-th route knowledge, p3 ik (O j ) represents the current position matching membership degree between the i-th member in the trajectory data and the k-th route in the j-th route knowledge, n represents the number of formation members in the trajectory data, m j represents the number of routes in the j-th route knowledge, r3 ijk represents the Euclidean distance between the current position of the i-th member in the trajectory data and the position of the k-th route in the j-th route knowledge, r3 jk represents the distance threshold of the k-th route in the j-th route knowledge, generally set to 5000 meters, x1 i is the x coordinate of the i-th formation member in the trajectory data, y1 i is the y coordinate of the i-th formation member in the trajectory data, z1 i is the z coordinate of the i-th formation member in the trajectory data, x2 jkl is the x coordinate of the l-th point of the k-th route in the j-th route knowledge, y3 jkl is the y coordinate of the l-th point of the k-th route in the j-th route knowledge, z3 jkl is the z coordinate of the l-th point of the k-th route in the j-th route knowledge, m jk represents the number of trajectory points of the k-th route in the j-th route knowledge, and min represents taking the minimum value.

[0133] In the above processing flow of constructing evidence for route intention recognition, the calculation formula for calculating the evidence of route intention recognition based on the route matching membership degree is as follows:

[0134]

[0135] p3(Ω) = 1 - max{p3(O j )|j = 1, 2,.., m}

[0136] Among them, p3(O j ) represents the route matching membership degree between the trajectory data and the j-th route knowledge, O j represents the intention name in the j-th route knowledge, Ω represents the uncertainty of the intention, p3(Ω) represents the uncertainty degree of the route intention recognition evidence, and m is the number of knowledge items.

[0137] Refer to Figure 6 . The processing flow of the above-mentioned intention recognition result of generating the sea formation target is as follows:

[0138] Perform the product of the confidence degrees of intention evidence;

[0139] Perform the fusion of the confidence degrees of the comprehensive intention evidence;

[0140] Perform the comprehensive intention recognition decision and give the intention recognition result.

[0141] In the above-mentioned processing flow of the intention recognition result of generating the sea formation target, the product formula for the product of the confidence degrees of intention evidence is:

[0142]

[0143] Among them, m1(o j ) is the confidence degree of the formation intention recognition evidence for the intention o j , m2(o j ) is the confidence degree of the position intention recognition evidence for the intention o j , m3(o j ) is the confidence degree of the route intention recognition evidence for the intention o j , m1(Ω) is the confidence degree of the formation intention recognition evidence for the intention Ω, m2(Ω) is the confidence degree of the position intention recognition evidence for the intention Ω, m3(Ω) is the confidence degree of the route intention recognition evidence for the intention Ω, and s(Ω) represents the maximum confidence degree of the intention evidence for Ω.

[0144] In the above-mentioned processing flow of the intention recognition result of generating the sea formation target, the fusion formula for the fusion of the confidence degrees of the comprehensive intention evidence is:

[0145]

[0146] Among them, m(O j ) is the confidence degree of the comprehensive intention evidence for the intention o j , and m(Ω) is the confidence degree of the comprehensive intention evidence for Ω.

[0147] In the above-mentioned processing flow of the intention recognition result of generating the sea formation target, the processing flow of the comprehensive intention recognition decision is:

[0148] Determine whether m(Ω)>TH1 (which can be set according to experience and actual needs, for example, set to 0.5) holds. If it holds, the intention recognition fails, and the judgment result of the intention recognition is "unclear intention".

[0149] Calculate the maximum value of the comprehensive evidence synthesis result. The calculation formula is:

[0150] m(O max ) = max{m(O j )|j = 1, 2,..., m},

[0151] where m(O max ) represents the maximum value of the comprehensive evidence synthesis result;

[0152] Determine whether m(O max )>TH2 (which can be set according to experience and actual needs, for example, set to 0.8) holds. If it holds, the recognition is successful, and the judgment result of the intention recognition is the intention name O j , otherwise the recognition fails, and the judgment result of the intention recognition is "unclear intention".

[0153] Based on the same technical concept, as Figure 7 shown, an embodiment of the present invention provides a sea formation target intention recognition system, including:

[0154] A data acquisition module for acquiring sea formation target trajectory data;

[0155] A trajectory data preprocessing module for preprocessing the sea formation target trajectory data;

[0156] A formation intention recognition module for constructing formation intention recognition evidence for the sea formation target trajectory data after trajectory data preprocessing by using formation knowledge in the sea formation target intention recognition knowledge base;

[0157] A position intention recognition module for constructing position intention recognition evidence for the sea formation target trajectory data after trajectory data preprocessing by using position knowledge in the sea formation target intention recognition knowledge base;

[0158] A route intention recognition module for constructing route intention recognition evidence for the sea formation target trajectory data after trajectory data preprocessing by using route knowledge in the sea formation target intention recognition knowledge base;

[0159] An intention comprehensive recognition module for comprehensively recognizing the formation intention recognition evidence, position intention recognition evidence, and route intention recognition evidence, and generating an intention recognition result of the sea formation target.

[0160] Regarding the specific processing methods of the various modules in the above system, reference may be made to the specific description of the above method, which will not be elaborated here.

[0161] Based on the same technical concept, an embodiment of the present invention further provides an electronic device, which can implement the method flow of the sea formation target intention recognition method provided in the above embodiments of the present invention. In one embodiment, the electronic device may be a server, or a terminal device or other electronic devices. As Figure 8 shown, the electronic device may include:

[0162] At least one processor, and a memory connected to the at least one processor. In the embodiments of the present invention, the specific connection medium between the processor and the memory is not limited. Figure 8 In [description], it is taken as an example that the processor and the memory are connected through a bus. The bus is Figure 8 shown by a thick line in [description]. The connection manners between other components are only for illustrative purposes and are not limited thereto. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 8 it is only shown by a thick line in [description], but it does not mean that there is only one bus or one type of bus. Alternatively, the processor can also be called a controller, and there is no limit to the name.

[0163] In the embodiments of the present invention, the memory stores instructions executable by the at least one processor. The at least one processor can execute the instructions stored in the memory to execute a sea formation target intention recognition method described above. The processor can implement Figure 8 the functions of each module in the device shown in [description].

[0164] Among them, the processor is the control center of the device, and can connect various parts of the entire control device through various interfaces and lines. By running or executing the instructions stored in the memory and calling the data stored in the memory, various functions of the device and process data, so as to monitor the device as a whole.

[0165] In an alternative design, the processor may include one or more processing units. The processor may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface and application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above modem processor may not be integrated into the processor. In some embodiments, the processor and the memory can be implemented on the same chip, and in some embodiments, they can also be separately implemented on independent chips.

[0166] The processor can be a general-purpose processor, such as a CPU, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of a method for identifying the intention of a sea formation target disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by a hardware processor, or executed and completed by a combination of hardware and software modules in the processor.

[0167] As a non-volatile computer-readable storage medium, the memory can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The memory can include at least one type of storage medium. For example, it can include flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic memory, magnetic disk, optical disc, and so on. The memory is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in the embodiments of the present invention can also be a circuit or any other device capable of implementing a storage function, for storing program instructions and / or data.

[0168] By designing and programming the processor, the code corresponding to the method for identifying the intention of a sea formation target introduced in the foregoing embodiments can be solidified into the chip, so that the chip can execute the steps of the method in the foregoing embodiments when running. How to design and program the processor is a well-known technology to those skilled in the art and will not be elaborated here.

[0169] Based on the same inventive concept, the embodiments of the present invention also provide a storage medium that stores computer instructions. When the computer instructions run on a computer, the computer is caused to execute a method for identifying the intention of a sea formation target discussed above.

[0170] In some alternative embodiments, aspects of the method for identifying the intention of a sea formation target provided by the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a device, the program code is used to cause the control device to execute the steps in the method for identifying the intention of a sea formation target according to various exemplary embodiments of the present invention described above in this specification.

[0171] It should be noted that although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more of the above-mentioned units can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units. In addition, although the operations of the method of the present invention are described in a specific order in the drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution.

[0172] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0173] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a server, such that the instructions executed by the processor of the computer or other programmable data processing device generate a device for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0174] Program code for performing the operations of the present invention may be written using any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computing device, partially on the user device, execute as a stand-alone software package, execute partially on the user's computing device and partially on a remote computing device, or execute entirely on a remote computing device or server.

[0175] In the case of a remote computing device, the remote computing device may be connected to the user's computing device through any type of network including a local area network (LAN) or a wide area network (WAN), or alternatively, may be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0176] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one process Figure 1 one process or multiple processes and / or boxes Figure 1 specified in one box or multiple boxes.

[0177] These computer program instructions may also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or boxes Figure 1 specified in one box or multiple boxes.

[0178] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention may have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for identifying the intention of a sea formation target, characterized in that, Including: Obtain the trajectory data of the sea formation target; Perform trajectory data preprocessing on the trajectory data of the sea formation target; For the trajectory data of the sea formation target after trajectory data preprocessing, utilize the formation knowledge, position knowledge, and route knowledge in the sea formation target intention recognition knowledge base to construct formation intention recognition evidence, position intention recognition evidence, and route intention recognition evidence respectively; Perform comprehensive recognition on the formation intention recognition evidence, position intention recognition evidence, and route intention recognition evidence to generate the intention recognition result of the sea formation target.

2. The method for identifying the intention of a sea formation target according to claim 1, wherein The trajectory data preprocessing includes: Classify and save trajectory points according to the target number, and group the trajectory points with the same target number into the same category; Eliminate illegal values for the same category of trajectories, and eliminate the illegal values in the trajectories; Perform trajectory compression and alignment on the same category of trajectories, compress the trajectories and align them to the same time position.

3. The method for identifying the intention of a sea formation target according to claim 2, characterized in that, The method of classifying and saving trajectory points according to the target number and grouping the trajectory points with the same target number into the same category is: arrange the trajectory points with the same target number in ascending order of time and save them into the same linked list in sequence, with the one with smaller time at the head of the linked list and the one with larger time at the tail of the linked list.

4. The method for identifying the intention of a sea formation target according to claim 3, characterized in that, The method of eliminating illegal values is: calculate the trajectory speed of the trajectories in the same linked list in sequence from the second trajectory point at the head to the last trajectory point at the tail. If the trajectory speed of this trajectory point is greater than the preset speed threshold, then this trajectory point is an illegal value and is removed from the linked list.

5. The method for identifying the intention of a sea formation target according to claim 4, wherein The method of calculating the trajectory speed is: divide the Euclidean distance between this trajectory point and the previous trajectory point by the time difference between this trajectory point and the previous trajectory point to obtain the trajectory speed.

6. The method for identifying the intention of a sea formation target according to claim 2, wherein The performing trajectory compression and alignment on the same category of trajectories includes: Segment the trajectory points according to the time period, and group the trajectory points with the same target number belonging to the same period into the same segment; Perform trajectory compression and alignment on the same segment of trajectories, and compress the same segment of trajectory points into one trajectory point.

7. The method for identifying the intention of a sea formation target according to claim 6, characterized in that, The segmenting the trajectory points according to the time period includes: Find the minimum time and maximum time of all trajectory points; Based on the minimum time, maximum time, and the preset time period for compression and alignment, calculate the number of segments after segmentation; Based on the minimum time and the preset time period for compression and alignment, calculate the middle time of each segment.

8. The method for identifying the intention of a sea formation target according to claim 7, characterized in that, The performing trajectory compression and alignment on the same segment of trajectories includes: Traverse the middle time of each segment, and search for the trajectory points in the same trajectory that belong to the same segment as the segment where the middle time is located according to the time; For the searched trajectory points, find the two trajectory points with the smallest time difference from the middle time. If the number of trajectory points in a certain segment is less than 2, then this segment is not compressed. Otherwise, for the two found trajectory points and the middle time, use the two-point interpolation formula to calculate the trajectory point after compression and alignment.

9. The method for identifying the intention of a sea formation target according to claim 1, wherein Constructing the formation intention recognition evidence includes: Obtain the trajectory data of a sea formation target to be recognized after trajectory data preprocessing; For the trajectory data of this sea formation target, traverse the formation knowledge in the sea formation target intention recognition knowledge base, and calculate the formation matching membership degree according to the positions of the formation members in the trajectory data and the formation knowledge; Calculate the formation intention recognition evidence according to the formation matching membership degree.

10. The method for identifying the intention of a sea formation target according to claim 1, characterized in that, Constructing the position intention recognition evidence includes: Obtain the trajectory data of a sea formation target to be recognized after preprocessing of trajectory data; For the trajectory data of the sea formation target, traverse the formation knowledge in the knowledge base for intention recognition of the sea formation target, and calculate the formation matching membership degree according to the positions of the formation members in the trajectory data and the formation knowledge; Calculate the formation intention recognition evidence according to the formation matching membership degree.

11. The method for identifying the intention of a sea formation target according to claim 1, characterized in that, Constructing the evidence for route intention recognition includes: Obtain the trajectory data of a sea formation target to be recognized after preprocessing of trajectory data; For the trajectory data of the sea formation target, traverse the route knowledge in the knowledge base for intention recognition of the sea formation target, and calculate the route matching membership degree according to the trajectories of the formation members in the trajectory data and the route knowledge; Calculate the route intention recognition evidence according to the route matching membership degree.

12. A sea formation target intention recognition system, characterized in that, Including: A data acquisition module for obtaining the trajectory data of the sea formation target; A trajectory data processing module for preprocessing the trajectory data of the sea formation target; A formation intention recognition module for constructing formation intention recognition evidence for the trajectory data of the sea formation target after preprocessing of the trajectory data, using the formation knowledge in the knowledge base for intention recognition of the sea formation target; A formation position intention recognition module for constructing formation position intention recognition evidence for the trajectory data of the sea formation target after preprocessing of the trajectory data, using the formation position knowledge in the knowledge base for intention recognition of the sea formation target; A route intention recognition module for constructing route intention recognition evidence for the trajectory data of the sea formation target after preprocessing of the trajectory data, using the route knowledge in the knowledge base for intention recognition of the sea formation target; An intention comprehensive recognition module for comprehensively recognizing the formation intention recognition evidence, formation position intention recognition evidence and route intention recognition evidence, and generating an intention recognition result of the sea formation target.

Images