Intelligent connected vehicle path planning method based on homomorphic encryption

Abstract

The present application relates to homomorphism encryption and automobile path planning technical field, specifically to intelligent networked automobile path planning method based on homomorphism encryption, including: obtaining city related information of target city, and generating city distance matrix; the city distance matrix is encrypted through homomorphism encryption algorithm, and the corresponding homomorphism encryption distance matrix is generated;Optimal path solving is carried out based on homomorphism encryption distance matrix through genetic algorithm, and encrypted local optimal solution is generated;The encrypted local optimal solution is decrypted, and the corresponding local optimal path information is obtained;All local optimal path information is compared, and whether the termination condition is reached is judged: if yes, then path planning is realized based on the current optimal local optimal path information.The present application can homomorphically encrypt the data transmitted by the driving terminal and the server terminal, and can realize path planning based on homomorphic ciphertext data, so as to improve the effectiveness and data security of automobile path planning.

Description

Technical Field

[0001] This invention relates to the fields of homomorphic encryption and vehicle routing technology, specifically to a method for intelligent connected vehicle routing based on homomorphic encryption. Background Technology

[0002] The Internet of Vehicles (IoV) refers to the use of onboard devices in vehicles via wireless communication technology to effectively utilize all dynamic vehicle information on an information network platform, providing various functional services during vehicle operation. As a currently popular research area within the Internet of Things (IoT), the IoV makes significant contributions to alleviating traffic congestion, resource allocation, and road route planning.

[0003] Intelligent Connected Vehicles (ICVs) are an organic combination of vehicle-to-everything (V2X) and intelligent vehicles, with path planning being a crucial task. While ICVs possess a certain level of computing power, the computational load for path planning is enormous. Performing path planning calculations on the vehicle's end would result in low efficiency and poor effectiveness. Therefore, ICVs typically upload vehicle-side data to a server for path planning calculations; the server then distributes the calculated path information back to the vehicle for path planning.

[0004] However, during the process of the vehicle uploading data to the server and the server sending route information back to the vehicle, leakage of vehicle data and route information is easily possible. Vehicle data pertains to user privacy, and route information relates to user driving safety, leading to compromised security in the vehicle system's route planning. Therefore, designing a method that ensures the effectiveness of route planning and improves data security is a pressing technical problem that needs to be solved. Summary of the Invention

[0005] To address the shortcomings of the existing technologies, the technical problem to be solved by this invention is: how to provide a path planning method for intelligent connected vehicles based on homomorphic encryption, which can homomorphically encrypt the data transmitted between the vehicle and the server, and can realize path planning based on homomorphic ciphertext data, thereby improving the effectiveness and data security of vehicle path planning, and providing a new approach for path planning of intelligent connected vehicles.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0007] A path planning method for intelligent connected vehicles based on homomorphic encryption includes:

[0008] S1: Obtain relevant city information for the target city and generate a city distance matrix;

[0009] S2: Encrypt the city distance matrix using a homomorphic encryption algorithm to generate the corresponding homomorphic encrypted distance matrix;

[0010] S3: Generate a local optimum solution for encryption by solving the optimal path based on the homomorphic encryption distance matrix using a genetic algorithm;

[0011] S4: Decrypt the encrypted local optimal solution to obtain the corresponding local optimal path information;

[0012] S5: Compare all the local optimal path information and determine whether the termination condition has been met: if yes, proceed to step S6; otherwise, proceed to step S3.

[0013] S6: Implement path planning based on the current best local optimal path information.

[0014] Preferably, the city-related information for the target city includes the city code and the city's geographical location;

[0015] In step S1, a corresponding city distance matrix is ​​generated based on the city number and geographical location of all target cities. Each element in the city distance matrix is ​​a distance value, and the distance value with horizontal coordinate i and vertical coordinate j in the city distance matrix represents the distance between the target city with city number i and the target city with city number j.

[0016] Preferably, the city distance matrix is ​​homomorphically encrypted using the Paillier homomorphic encryption algorithm.

[0017] Preferably, the Paillier homomorphic encryption algorithm implements homomorphic encryption using the following formula:

[0018] c = g m r n mod n 2 ;

[0019] Wherein, the public key pk = (n, g);

[0020] In the formula: c represents the encrypted ciphertext; m represents the data before encryption; g represents generating an n-order subgroup; r represents a random number; pk represents a public key packet.

[0021] Preferably, in step S3, the genetic algorithm solves for the optimal path through the following steps:

[0022] S301: Define the fitness function; then randomly generate several chromosomes as a population, each chromosome representing a path sequence composed of the city number and geographical location of each target city;

[0023] S302: Select several excellent chromosomes as parent chromosomes based on the fitness function;

[0024] S303: Selecting, crossing over, and mutating parent chromosomes to generate new chromosomes;

[0025] S304: Calculate the fitness of each chromosome based on the fitness function, and select several excellent chromosomes as a new population;

[0026] S305: Determine whether the set threshold number of attempts has been reached: if yes, proceed to step S306; otherwise, proceed to step S302.

[0027] S306: Output the optimal path sequence corresponding to the chromosome as the local optimum for encryption in this round.

[0028] Preferably, in step S302, the generated chromosome is transcoded using the following formula:

[0029]

[0030] Where: b0, b1, b n-1 b i Indicates a city code containing either 0 or 1; x t Represents decimal data.

[0031] Preferably, in step S304, the selection, crossover, and mutation operations are performed using selection operators, crossover operators, and mutation operators;

[0032] The selection operator is used to traverse the sum of distances of the path sequence in this round. The smaller the fitness, the shorter the distance of the current path sequence and the better the individual. The smallest individual is the encrypted local optimum solution calculated in this round.

[0033] The crossover operator uses two different chromosomes to exchange partial chromosome segments;

[0034] Mutation operators generate new chromosomes by changing the numbered position pairs within the same chromosome segment.

[0035] Preferably, in step S4, decryption is achieved using the following formula:

[0036] m = L(c λ mod n 2 )*u;

[0037] in, Private key sk = (λ, u);

[0038] λ = lcm(p-1, q-1);

[0039] u=(L(gλ mod n 2 )) -1 mod n;

[0040] In the formula: m represents the decrypted data; c represents the ciphertext before decryption; n represents the product of two prime numbers p and q; λ represents the least common multiple of two prime numbers p and q; u represents the parameter value used in the encryption function; sk represents the private key; lcm represents the output of the least common multiple of the two numbers.

[0041] Preferably, in step S5, the termination condition refers to: the current optimal local optimal path information has reached the optimal, or the number of iterations has reached a preset threshold number of iterations.

[0042] Compared with existing technologies, the intelligent connected vehicle path planning method based on homomorphic encryption in this invention has the following advantages:

[0043] In this invention, the data uploaded and transmitted between the vehicle terminal and the server terminal is homomorphically encrypted ciphertext data. This homomorphically encrypted ciphertext data can be subjected to addition or multiplication operations in ciphertext, and the resulting ciphertext is identical to the corresponding plaintext operation result. This enables route planning without revealing the plaintext, preventing the server terminal from obtaining driving information (i.e., city-related information) and optimal route information during the optimal route solution process. Even if data leakage occurs during data transmission, only the encrypted homomorphically encrypted ciphertext data is leaked, without compromising user privacy or affecting user driving safety. This improves the security of vehicle route planning and provides a new approach to route planning for intelligent connected vehicles.

[0044] This invention uses a genetic algorithm based on a homomorphic encrypted distance matrix to solve for the optimal path. Although the Traveling Salesman Problem is an NP-complete problem, it is difficult to find the optimal path when the problem size is large. However, the genetic algorithm can effectively solve for the shortest path to traverse the target city through evolutionary iteration, and can seek a relatively optimal solution, thereby improving the effectiveness of car route planning. Attached Figure Description

[0045] To make the objectives, technical solutions, and advantages of the invention clearer, the invention will now be described in further detail with reference to the accompanying drawings, wherein:

[0046] Figure 1 This is a logical block diagram of a path planning method for intelligent connected vehicles based on homomorphic encryption.

[0047] Figure 2 This is a schematic diagram of network communication between the vehicle terminal and the server terminal.

[0048] Figure 3This is a flowchart illustrating the homomorphic encryption computation process.

[0049] Figure 4 This refers to the transposition method of the cross operator;

[0050] Figure 5 This describes how the mutation operator works.

[0051] Figure 6 This is a graph showing the trend of fitness changes during the evolution of a genetic algorithm.

[0052] Figure 7 This is the optimal city traversal path map generated in the example. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. 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 invention, but only to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0054] It should be noted that similar reference numerals and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the figures, or the orientation or positional relationship commonly used when the product is in use. They are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third," etc., are only used to distinguish descriptions and should not be construed as indicating or implying relative importance. In addition, the terms "horizontal," "vertical," etc., do not mean that the component is required to be absolutely horizontal or suspended, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted. In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0055] The following detailed explanation illustrates the specific implementation methods:

[0056] Example:

[0057] This embodiment discloses a path planning method for intelligent connected vehicles based on homomorphic encryption.

[0058] like Figure 1 As shown, the intelligent connected vehicle path planning method based on homomorphic encryption includes:

[0059] S1: (Driving end) Obtain city-related information of the target city and generate a city distance matrix;

[0060] In this embodiment, the target city is n nodes in a coordinate system, and the car needs to traverse the marked cities in the coordinate system. The starting point is also the ending point. For example, starting from city A, it needs to traverse B, C, D, ..., Z. The purpose of this invention is to find the shortest traversal distance so that the car can plan the route information in advance before departure.

[0061] S2: (Driving end) The city distance matrix is ​​homomorphically encrypted using the Paillier homomorphic encryption algorithm and then uploaded to the server.

[0062] S3: (Server side) The optimal path is solved by using a genetic algorithm based on the homomorphic encryption distance matrix, generating an encrypted local optimal solution and sending it to the vehicle terminal;

[0063] S4: (Train end) Decrypt the encrypted local optimal solution sent out to obtain the corresponding local optimal path information;

[0064] S5: (Train end) Compare all the local optimal path information and determine whether the termination condition has been met: if yes, proceed to step S6; otherwise, proceed to step S3 and upload the encrypted local optimal solution corresponding to the current optimal local optimal path information to the server.

[0065] In this embodiment, the termination condition refers to: the current optimal local optimal path information has reached the optimal, or the number of iterations has reached a preset threshold number of iterations.

[0066] The driver needs to compare the decrypted optimal route information locally, discarding longer routes. The comparison information is then encrypted and sent back to the server, which performs the sorting process. This process is repeated N times before selecting the optimal route value to obtain the best result.

[0067] S6: (Driving end) Implements route planning based on the current best local optimal path information.

[0068] In this embodiment, combined with Figure 2 As shown, the vehicle terminal communicates and interacts with the server through the roadside unit.

[0069] This invention encrypts the city distance matrix using a homomorphic encryption algorithm and uploads it to a server. The server then uses a genetic algorithm to solve for the optimal path, generating an encrypted local optimum solution and sending it to the vehicle. The vehicle decrypts the encrypted local optimum solution to obtain the local optimum path information, and then selects the optimal local optimum path through path comparison to achieve route planning. On one hand, the data uploaded and transmitted between the vehicle and the server in this invention is homomorphically encrypted ciphertext data. Homomorphic ciphertext data can be added or multiplied in its ciphertext state, and the resulting ciphertext is identical to the corresponding plaintext operation result. This allows for route planning without revealing the plaintext, preventing the server from obtaining driving information (i.e., city-related information) and the optimal path information during the optimal path solution process. Even if data leakage occurs during data transmission, only the encrypted homomorphic ciphertext data is leaked, without compromising user privacy or affecting driving safety. This improves the security of vehicle route planning and provides a new approach for route planning in intelligent connected vehicles. On the other hand, this invention uses a genetic algorithm to solve for the optimal path based on a homomorphic encrypted distance matrix. Although the Traveling Salesman Problem is an NP-complete problem and it is difficult to find the optimal path when the problem size is large, the genetic algorithm can effectively solve for the shortest path to traverse the target city through evolutionary iteration, and can seek a relatively optimal solution, thereby improving the effectiveness of car route planning.

[0070] This invention generates a distance matrix based on city-related information for two reasons: First, it better satisfies the additive homomorphism of Paillier homomorphism, and the coordinates are not zero; second, the distance matrix can be more intuitively and conveniently understood and calculated by computers.

[0071] In the specific implementation process, the relevant information of the target city includes the city number and the city's geographical location (i.e., coordinates); the driving terminal needs to serialize each target city to obtain the city number, as shown in Table 1.

[0072] Table 1 City Numbers

[0073]

[0074] After obtaining the city ID and corresponding geographic coordinates of each target city, a city distance matrix is ​​generated based on the city ID and geographic location of all target cities. Each element in the city distance matrix is ​​a distance value, and the distance value with x-coordinate i and y-coordinate j represents the distance between target city i and target city j. The initial arrangement of the city distance matrix needs to be calculated and generated automatically on the vehicle's end.

[0075] The formula for the initial city distance matrix is ​​described as follows:

[0076]

[0077] This invention generates a distance matrix based on city-related information for two reasons: First, it better satisfies the additive homomorphism of Paillier homomorphism, and the coordinates are not zero; second, the distance matrix can be more intuitively and conveniently understood and calculated by computers.

[0078] In the specific implementation process, the city distance matrix is ​​homomorphically encrypted using the Paillier homomorphic encryption algorithm.

[0079] In this embodiment, the Paillier homomorphic encryption algorithm is used, which is a public-key encryption scheme capable of homomorphic encryption. Homomorphic encryption is a special type of encryption that allows addition, subtraction, multiplication, and other operations to be performed on the ciphertext without requiring decryption. This makes homomorphic encryption widely applicable in fields such as cloud computing and secure multi-party computation.

[0080] The basic idea behind the Paillier homomorphic encryption scheme is to use the multiplicative congruence property of large integers to encrypt plaintext into a large integer, and then use the congruence property of this large integer to achieve homomorphic encryption. The security of the Paillier homomorphic encryption scheme is based on the difficulty of the discrete logarithm problem and the RSA problem. The Paillier homomorphic encryption scheme has high security and flexibility, and is therefore widely used in fields such as cloud computing, secure multi-party computation, and data privacy protection.

[0081] The overall process of homomorphic encryption is as follows: Figure 3 As shown in the diagram. The `keygen` function module generates the public and private keys; the `Epk` module is the encryption function module, which encrypts the initial plaintext; the `Dsk` module is the decryption function module, which decrypts the ciphertext; and the last two lines represent that multiplying the ciphertext is equivalent to adding the plaintext.

[0082] Specifically:

[0083] The vehicle runs a Paillier cryptosystem key generation algorithm locally to obtain a public-private key pair, and discloses the public key to the server by keeping the private key to itself.

[0084] The formula for generating public-private key pairs is described below:

[0085] Choose two large prime numbers p and q. Then:

[0086] gcd(pq,(p-1)(q-1)=1;

[0087] n = pq; λ = lcm(p-1, q-1);

[0088] By randomly selecting a number less than n 2 A positive integer g. And there exists a positive integer g such that:

[0089] u=(L(g λ mod n 2 )) -1 mod n;

[0090] At this point, the public key has been formed, namely the public key pk = (n, g) and the private key sk = (λ, u).

[0091] In this embodiment, the generated public-private key pair is as follows:

[0092]

[0093] After the city distance matrix is ​​formed in plaintext, according to c=g m r n mod n 2 A cryptographic city distance matrix is ​​formed.

[0094] In other words, the Paillier homomorphic encryption algorithm achieves homomorphic encryption through the following formula:

[0095] c = g m r n mod n 2 ;

[0096] Wherein, the public key pk = (n, g);

[0097] In the formula: c represents the encrypted ciphertext; m represents the data before encryption; g represents generating an n-order subgroup; r represents a random number; pk represents a public key packet.

[0098] The formula for converting the city distance matrix to the homomorphic encrypted distance matrix is ​​described as follows:

[0099]

[0100] This invention encrypts the city distance matrix using the Paillier homomorphic encryption algorithm and uploads it to the server. The Paillier homomorphic encryption scheme has high security and flexibility, and can better achieve route planning without revealing plaintext. This prevents the server from obtaining driving information (i.e., city-related information) and optimal route information during the process of solving the optimal route. Even if data leakage occurs, only the encrypted homomorphic ciphertext data will be leaked, without revealing the user's personal privacy or affecting the user's driving safety, thereby further improving the security of car route planning.

[0101] In practice, after the homomorphic encrypted distance matrix is ​​formed on the vehicle side, it is uploaded to the server using roadside units. The server directly calculates the encrypted city distance matrix using the homomorphic encryption algorithm, without needing to perform decryption calculations. The explanation for not needing decryption calculations is as follows:

[0102] For two ciphertexts, we have:

[0103]

[0104]

[0105]

[0106] r1 and r2 are both The elements in the array, therefore r1·r2 also belong to the same category. Furthermore, they share the same properties, so c1·c2 can be considered as ciphertext encrypted with m = m1 + m2, and the decryption result of c1·c2 is m. Therefore, the server can directly calculate the result without decrypting the private data.

[0107] In the specific implementation process, the genetic algorithm used is as follows: Let there be a set of n cities C = {C1, C2, ..., C...} n Let the distance between the two cities be d. ij =d(C i C j If we calculate the city traversal sequence, then we can obtain {C}. I(1) C I(2) ,...,C I(n)}, making Where I(1), I(2), ..., I(n) is a permutation of 1, 2, ..., n.

[0108] The genetic algorithm used here first initializes the original data population, then initializes and evaluates the distance matrix between encrypted cities. If t < T, the original combinations are shuffled through selection, crossover, and mutation, and then re-evaluated. If t > T, the calculation terminates and the result is output. Therefore, this round of calculation yields the shorter path length. On the server side, it only knows the cities numbered 0 to n-1 but not their specific names, so it uses 0 to n-1 to represent the path through the cities. Therefore, the solution can be represented as: {sum} = (n-1)!.

[0109] From a graph theory perspective, n cities can be viewed as a weighted undirected graph g = (v, e), where v is the set of vertices (each city), and e is the set of edges (the roads connecting any two cities). Let d = (d_ij) be the city distance matrix, consisting of the distances between vertices i and j (the matrix of lengths of the roads connecting the i-th and j-th cities). The Traveling Salesman Problem (TSP) aims to find a path that passes through each vertex exactly once, forms a complete closed cycle, and has the minimum cumulative length. {sum} = (n-1)! is the sum of the number of all possible paths.

[0110] Specifically, the genetic algorithm solves for the optimal path through the following steps:

[0111] S301: Define the fitness function; then randomly generate several chromosomes as a population, each chromosome representing a path sequence composed of the city number and geographical location of each target city;

[0112] In this embodiment, the fitness function is used to evaluate the quality of each chromosome. The fitness function can be the path length or the reciprocal of the path time, etc.

[0113] S302: Select several excellent chromosomes as parent chromosomes based on the fitness function;

[0114] In this embodiment, the chromosome generated from the encrypted local optimal solution corresponding to the current optimal local optimal path information is taken as the optimal chromosome.

[0115] S303: Selecting, crossing over, and mutating parent chromosomes to generate new chromosomes;

[0116] In this embodiment, selection, crossover, and mutation operations are performed using selection, crossover, and mutation operators;

[0117] The selection operator is used to iterate through the sum of distances in the current round's path sequence. A lower fitness indicates a shorter distance in the current path sequence and a more excellent individual. The smallest individual is the encrypted local optimum for this round of computation. The tournament principle is used to select the chromosomes with the lowest fitness from each generation of the population as elite chromosomes, with the smallest chromosome representing the local optimum.

[0118] The crossover operator uses two different chromosomes to exchange partial chromosome segments; this exchange may result in conflicts due to identical chromosome numbers, and the solution is to continuously adjust until no conflicts exist. Figure 4 As shown, within a certain range of a chromosome, the crossover operator will scramble the sequence of that part of the chromosome, thereby regenerating a new chromosome and thus scrambling the city sequence to generate a new route.

[0119] Mutation operators achieve evolution by changing the numbered pairs within the same chromosome segment, thus creating new chromosomes. Figure 5 As shown, the positions of chromosomes 3 and 8 in the original normal sequence are swapped to form a new chromosome, thereby generating a new city route.

[0120] S304: Calculate the fitness of each chromosome based on the fitness function, and select several excellent chromosomes as a new population;

[0121] In this embodiment, fitness is the path length. Based on the planned path, the total distance is calculated, and the total distance is the fitness. The lower the fitness, the better the effect.

[0122] S305: Determine whether the set threshold number of attempts has been reached: if yes, proceed to step S306; otherwise, proceed to step S302.

[0123] S306: Output the optimal path sequence corresponding to the chromosome as the local optimum for encryption in this round.

[0124] like Figure 6 As shown, the fitness curve changes during the iterative evolution of the genetic algorithm. The horizontal and vertical axes represent the number of generations and the path length required for traversal, respectively. Initially, the path length reaches 650, which is significantly lower than the expected shortest path length. As the number of generations increases, the path length continuously decreases until it approaches the shortest path length, i.e., the optimal path length, around the 280th generation.

[0125] This invention uses the aforementioned genetic algorithm to solve for the optimal path based on the homomorphic encrypted distance matrix. Although the Traveling Salesman Problem is an NP-complete problem, finding the optimal path is difficult when the problem size is large. However, the genetic algorithm can effectively solve the shortest path to traverse the target city through evolutionary iteration, thus solving the NP-complete Traveling Salesman Problem and further improving the effectiveness of car route planning.

[0126] In the specific implementation process, the generated chromosome is transcoded using the following formula:

[0127]

[0128] Where: b0, b1, b n-1 b i Indicates a city code containing either 0 or 1; x t Represents a decimal number.

[0129] This invention uses the above formula to convert the generated (binary) chromosome into decimal, making it easier to observe the results of the calculation and thus improving the effectiveness of vehicle route planning.

[0130] In practice, decryption is achieved using the following formula:

[0131] m = L(c λ mod n 2 )*u;

[0132] in, Private key sk = (λ, u);

[0133] λ = lcm(p-1, q-1);

[0134] u=(L(g λ mod n 2 )) -1 mod n;

[0135] In the formula: m represents the decrypted data; c represents the ciphertext before decryption; n represents the product of two prime numbers p and q; λ represents the least common multiple of two prime numbers p and q; u represents the parameter value used in the encryption function; sk represents the private key; lcm represents the output of the least common multiple of the two numbers.

[0136] Figure 7 The optimal city traversal path map (path planning information) generated in this embodiment is based on traversing 15 cities. Each node simulates a different city on the map. After a series of algorithms, the optimal traversal route is finally calculated. It can be seen from the map that this route is the optimal route.

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit the technical solutions. Those skilled in the art should understand that any modifications or equivalent substitutions to the technical solutions of the present invention without departing from the spirit and scope of the present invention should be covered within the scope of the claims of the present invention.

Claims

1. A homomorphic encryption-based intelligent connected vehicle path planning method, characterized in that, Comprise: S1: obtain the city related information of target city, and generate city distance matrix; the city related information of target city includes city number and city geographical position; In step S1, the city distance matrix corresponding to all target cities is generated based on the city number and city geographical position of the target city; each element in the city distance matrix is a distance value, and the distance value with horizontal coordinate i and vertical coordinate j in the city distance matrix represents the distance between the target city with city number i and the target city with city number j; S2: encrypt the city distance matrix by homomorphic encryption algorithm to generate corresponding homomorphic encryption distance matrix; In step S2, the city distance matrix is homomorphically encrypted by paillier homomorphic encryption algorithm; Paillier homomorphic encryption algorithm realizes homomorphic encryption through the following formula: c = g m r n mod n 2 ; Wherein, public key pk=(n, g); In the formula: c represents the encrypted ciphertext; m represents the data before encryption; g represents the generation of n order subgroup; r represents a random number; pk represents a public key package; S3: solve the optimal path based on the homomorphic encryption distance matrix by genetic algorithm to generate encrypted local optimal solution; S4: decrypt the encrypted local optimal solution to obtain the corresponding local optimal path information; In step S4, the decryption is realized through the following formula: m = L(c λ mod n 2 )*u; wherein, Private key sk = (λ, u); Lambda=lcm(p-1, q-1); u = (L(g λ mod n 2 )) -1 mod n; In the formula: m represents the decrypted data; c represents the ciphertext before decryption; n represents the product of two prime numbers p and q; lambda represents the value of the least common multiple of two prime numbers p and q; u represents the parameter value used by the encryption function; sk represents the private key; lcm represents the output of the least common multiple of two numbers; S5: compare all the local optimal path information, and judge whether the termination condition is reached: if yes, execute step S6; otherwise, execute step S3; S6: realize path planning based on the current optimal local optimal path information.

2. The homomorphic encryption based intelligent vehicle path planning method of claim 1, wherein, In step S3, the genetic algorithm solves the optimal path through the following steps: S301: define fitness function; then randomly generate several chromosomes as population, each chromosome represents a path sequence composed of city number and city geographical position of each target city; S302: select several excellent chromosomes as parent chromosomes according to the fitness function; S303: select, cross and mutate the parent chromosomes to generate new chromosomes; S304: calculate the fitness of each chromosome according to the fitness function, and select several excellent chromosomes as new population; S305: judge whether the set number threshold is reached: if yes, execute step S306; otherwise, execute step S302; S306: output the path sequence corresponding to the optimal chromosome as the encrypted local optimal solution of this round.

3. The homomorphic encryption based intelligent vehicle path planning method of claim 2, wherein, In step S302, the generated chromosomes are converted through the following formula: wherein: b0, b1, b n-1 , b i denote city numbers containing 0 or 1; x t denotes data in decimal.

4. The homomorphic encryption based intelligent vehicle path planning method of claim 2, wherein, In step S304, the selection, crossover and mutation operations are performed by selection operator, crossover operator and mutation operator; The selection operator is used to traverse the distance sum of the path sequence of the round, and the smaller the fitness is, the shorter the distance of the current path sequence is, and the better the individual is, and the minimum individual is the encryption local optimal solution calculated in the round; The crossover operator uses two different chromosomes to exchange part of the chromosome segments; The mutation operator generates a new chromosome by changing the number position pairs in the same chromosome segment.

5. The homomorphic encryption based intelligent vehicle path planning method of claim 1, wherein: In step S5, the termination condition refers to that the current optimal local optimal path information has reached the optimum, or the number of loops reaches the preset loop number threshold.

Images