CN114519135A - Interest point recommendation method based on simulated annealing particle swarm algorithm - Google Patents
Interest point recommendation method based on simulated annealing particle swarm algorithm Download PDFInfo
- Publication number
- CN114519135A CN114519135A CN202011298454.3A CN202011298454A CN114519135A CN 114519135 A CN114519135 A CN 114519135A CN 202011298454 A CN202011298454 A CN 202011298454A CN 114519135 A CN114519135 A CN 114519135A
- Authority
- CN
- China
- Prior art keywords
- particle
- particle swarm
- algorithm
- interest
- interest point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0259—Targeted advertisements based on store location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an interest point recommendation method based on a simulated annealing particle swarm algorithm, which comprises the steps of generating an attribute information list according to an interest point type preselected by a user and influence factors of the interest point type; establishing an expression of an optimization solution algorithm objective function aiming at all types of interest point types; establishing an initial particle swarm, and setting initial particle swarm parameters of a simulated annealing particle swarm algorithm; updating the particle swarm and recording the optimal value; and outputting the particles corresponding to the optimal value of the objective function of the particle swarm, and taking the particles as recommended interest points. According to the scheme, the point of interest is efficiently recommended by using a simulated annealing algorithm and a particle swarm optimization method on the premise of comprehensively considering multiple independent variable influence factors. In the iterative process of particle swarm optimization solution, the idea of simulated annealing algorithm is utilized, and the annealing temperature is gradually reduced, so that the particle swarm algorithm of the particle swarm can be more quickly converged to the global optimal solution.
Description
Technical Field
The invention relates to the technical field of interest recommendation of an automobile cabin, in particular to an interest point recommendation method based on a simulated annealing particle swarm algorithm.
Background
The interest point recommendation problem is an important research problem in an intelligent cabin, and the optimized recommendation product of the interest point directly improves the comfort and experience of a driving user. The problem is also one of research hotspots integrating computer science, operation research, optimization science and other subjects in the academic world, and is closely related to the problems of city path planning, navigation planning, traffic scheduling, traffic flow control and the like in smart cities.
The current point of interest recommendation products mainly consider user evaluation information and perform sequencing recommendation by combining a user portrait and utilizing a big data recommendation algorithm. The main recommendation algorithms include collaborative filtering recommendation algorithms, regression algorithms and the like based on user information and article information, but the recommendation algorithms need to be established on the basis of user portrait data accumulation of more than millions of orders of magnitude, and need to be matched with an offline data training model, and the computational power requirement for online real-time recommendation is higher. In addition, the current algorithms are not convenient for comprehensive consideration such as: and influence factors of all aspects such as road information such as mileage distance and evaluation information, user preference information, interest point information and the like. Therefore, the point of interest recommendation using big data has the disadvantages of long time consumption and incapability of simultaneously considering multiple factors.
In order to solve the above problems of the big data recommendation algorithm, heuristic intelligent algorithms such as a particle swarm optimization algorithm and a genetic algorithm are widely applied to a fast solution of multi-objective optimization recommendation. The particle swarm optimization algorithm is widely applied to engineering due to strong robustness. However, the particle swarm optimization algorithm is easy to fall into a local optimal solution, which reduces the accuracy of point of interest recommendation.
Disclosure of Invention
The invention aims to solve the problems that in the prior art, the time consumption is long and multiple factors cannot be considered simultaneously in point of interest recommendation by using big data, and the particle swarm optimization algorithm is easy to fall into a local optimal solution, so that the accuracy of point of interest recommendation can be reduced.
In order to solve the problems, the embodiment of the invention discloses an interest point recommendation method based on a simulated annealing particle swarm algorithm, which comprises the following steps of:
s1: generating an attribute information list corresponding to each type of interest point set according to the type of the interest points preselected by the user and the influence factors of the type of the interest points; each attribute information list comprises the number of each interest point in the interest point set of the corresponding type and interest point influence factors;
s2: establishing an expression of an optimization solution algorithm objective function aiming at all types of interest point sets;
s3: establishing initial particle swarm aiming at all types of interest point sets, and setting initial particle swarm parameters of a simulated annealing particle swarm algorithm for the initial particle swarm; the initial particle swarm parameters comprise the number of particles of the initial particle swarm, the preset iteration steps of the initial particle swarm and the dimensionality of each particle in the initial particle swarm, and the dimensionality of each particle in the initial particle swarm corresponds to the number of the types of the interest points preselected by the user;
s4: calculating and recording an initial objective function value and a corresponding particle position of each particle in the initial particle swarm, and a swarm objective function historical optimum value and a corresponding particle position of the initial particle swarm according to an expression of an optimization solution algorithm objective function;
s5: setting annealing algorithm parameters of the simulated annealing particle swarm algorithm, and iteratively updating each particle in the initial particle swarm by utilizing the simulated annealing particle swarm algorithm according to the annealing algorithm parameters;
s6: calculating and recording the historical optimal value of the objective function of each particle and the corresponding particle position thereof in each generation of particle swarm after iterative update according to the expression of the objective function of the optimization solving algorithm, and the historical optimal value of the group objective function of each generation of particle swarm after iterative update and the corresponding particle position thereof; when the iteration step number of the updated particle swarm is equal to the preset iteration step number, ending the updating;
s7: and outputting the particles corresponding to the historical optimal value of the group objective function of the particle swarm, and taking the particles as recommended interest points.
By adopting the scheme, compared with the traditional recommendation algorithm based on big data, the method combining the simulated annealing algorithm and the particle swarm optimization is utilized, the problem of personalized recommendation of the interest points is solved, and the interest points are efficiently recommended on the premise of comprehensively considering multiple independent variable influence factors. In the iterative process of particle swarm optimization solution, the idea of simulated annealing algorithm is utilized, along with the gradual reduction of annealing temperature, so that the particle swarm can be converged to the global optimal solution more quickly compared with the traditional particle swarm algorithm.
According to another specific embodiment of the present invention, in the method for recommending a point of interest based on simulated annealing particle swarm optimization, step S1 includes:
s11: establishing an interest point list according to the type of interest points preselected by a user; wherein each interest point type comprises at least one interest point;
s12: acquiring influence factors of the types of the interest points;
s13: acquiring attribute information of the interest point set of the corresponding type according to the influence factors of each interest point type, and generating an attribute information list;
in step S12, the method for obtaining the influence factors of the user preselected interest point type includes:
obtaining the influence factors of the type of the point of interest preset by the user, or
And acquiring the influence factors of the default interest point type.
By adopting the scheme, the user can preselect the types of the interest points to be traversed according to actual requirements, construct the whole path process and then comb out the influence factors influencing the types of the preset interest points of the user. The personalized interest point recommendation is effectively realized under the condition of comprehensively considering various influence factors.
According to another specific embodiment of the present invention, in the method for recommending a point of interest based on a simulated annealing particle swarm algorithm disclosed by the embodiment of the present invention, the step S2 includes:
s21: respectively establishing a subfunction expression corresponding to each influence factor for each interest point type according to each influence factor of each interest point type;
s22: and performing summation operation on the subfunction expressions of all types of interest point sets to establish an expression of an optimization solution algorithm objective function.
According to another specific embodiment of the present invention, in the interest point recommendation method based on the simulated annealing particle swarm algorithm disclosed in the embodiment of the present invention, the step S2 further includes:
s23: setting constraint conditions for each influence factor of the interest point type; wherein the constraint condition comprises an equality condition and an inequality condition.
By adopting the scheme, the requirements of the user can be considered as much as possible by setting the constraint conditions for each influence factor, so that the interest points can be recommended more accurately.
According to another specific embodiment of the present invention, the method for recommending an interest point based on a simulated annealing particle swarm algorithm, which is disclosed by the embodiment of the present invention, the establishing of the initial particle swarm for all types of interest point sets includes:
s31: initializing particles in an initial particle swarm, and setting boundary conditions for the particles in the initial particle swarm;
s32: initializing an initialization velocity vector of particles in an initial particle swarm; wherein the initialization velocity vector is 0.5 to 0.7 times the initial value of the particle.
According to another specific embodiment of the present invention, in the interest point recommendation method based on the simulated annealing particle swarm algorithm disclosed in the embodiment of the present invention, the step S3 further includes:
and determining the initial particle number of the initial particle swarm and the preset iteration step number of the initial particle swarm according to the calculation principle of the shortest time required by convergence.
In the embodiment, the initial particle number of the initial particle swarm and the preset iteration step number of the initial particle swarm are determined according to the calculation principle of the shortest time required by convergence, so that the efficiency of the algorithm can be improved.
According to another specific embodiment of the present invention, in the method for recommending a point of interest based on a simulated annealing particle swarm algorithm disclosed in the embodiments of the present invention, in step S5, the annealing algorithm parameters include an initial annealing temperature, and the initial annealing temperature isAnd the number of the first and second electrodes,
setting annealing algorithm parameters of the simulated annealing particle swarm algorithm, and iteratively updating each particle in the initial particle swarm by utilizing the simulated annealing particle swarm algorithm according to the annealing algorithm parameters, wherein the steps of:
s51: calculating mutation probability of each particle according to an exponential probability formula, the current annealing temperature, the historical optimal value of the objective function of each particle and the historical optimal value of the group objective function of the particle swarm; the mutation probability is the approximation degree of the target function historical optimal value of each particle and the population target function historical optimal value of the particle swarm;
s52: determining the optimal particles in the contemporary particle group by using a roulette algorithm according to the distribution of the mutation probability;
s53: and moving each particle in each generation of particle swarm after iterative updating to a particle position corresponding to the target function historical optimal value of each particle and the optimal particle position in the current generation of particle swarm according to the self-learning rate, the swarm learning rate, the speed and speed inertial weight coefficient and the random rate between 0 and 1 so as to update each particle in each generation of particle swarm.
By adopting the scheme, in the iterative process of particle swarm optimization solution, a certain random probability is introduced by utilizing the idea of a simulated annealing algorithm, and the particle swarm can be more quickly converged to a global optimal solution compared with the traditional particle swarm optimization along with the gradual reduction of the annealing temperature.
According to another specific embodiment of the invention, the interest point recommendation method based on the simulated annealing particle swarm algorithm disclosed by the embodiment of the invention has the following exponential probability formula:
wherein p is the historical optimum value of the objective function of each particle; gbest is a group objective function historical optimal value of the particle swarm; and is
Updating each particle in each particle population according to the following formula:
Vk+1=C0*Vk+C1*rand*(Yk-Xk)+C2*rand*(Pgplus-Xk)
Xk+1=Xk+Vk+1
wherein the subscript k +1 represents the current iteration step number; v is the velocity vector of the particle; x is the current particle position; y is the particle position corresponding to the target function historical optimum value of the particle of the current particle; pgplusDetermining the optimal particles in the contemporary particle group by using a roulette algorithm under the contemporary iteration step number; c0Is a velocity inertial weight coefficient; c1Is the self-learning rate of the particle; c2Is the population learning rate of the particle.
By adopting the scheme, the self-learning rate of the particles, the group learning rate of the particles, the velocity inertia weight coefficient and the like are comprehensively considered in the process of updating the particle swarm, so that the updated particle swarm can rapidly move to the respective historical optimal value and the optimal particles of the group.
According to another specific embodiment of the present invention, after step S5, the method for recommending a point of interest based on a simulated annealing particle swarm algorithm disclosed in the embodiment of the present invention further includes the following steps:
s5': judging whether each dimension value of each particle exceeds a boundary condition or not;
if yes, returning the particles exceeding the boundary condition to the boundary condition;
if not, step S6 is executed.
By adopting the scheme, the dimensionality of each particle in each particle swarm after updating is judged, and the particles which do not meet the condition can be rapidly screened out, so that the calculation efficiency of the algorithm is higher.
According to another specific embodiment of the present invention, after step S6, the method for recommending a point of interest based on a simulated annealing particle swarm algorithm disclosed in the embodiment of the present invention further includes:
s6': updating the annealing temperature according to a preset proportionality coefficient; and, the annealing temperature is updated according to the following formula: t ═ T lambda, where T is the annealing temperature, lambda is a preset scaling factor, and the preset scaling factor ranges from 0 to 1 as a random number;
s6': judging whether the number of the iteration steps is equal to a preset iteration step number or not;
if yes, ending the iteration and executing S7;
if not, entering the next iteration.
By adopting the scheme, the annealing temperature is updated according to the preset proportional coefficient, and the particle swarm can more quickly converge to the global optimal solution compared with the traditional particle swarm algorithm along with the gradual reduction of the annealing temperature.
The beneficial effects of the invention are:
by adopting the scheme, compared with the traditional recommendation algorithm based on big data, the method combining the simulated annealing algorithm and the particle swarm optimization is utilized, the problem of personalized recommendation of the interest points is solved, and the interest points are efficiently recommended on the premise of comprehensively considering multiple independent variable influence factors. Furthermore, in the iterative process of particle swarm optimization solution, a certain random probability is introduced by using the idea of a simulated annealing algorithm, and the annealing temperature is updated according to a preset proportion coefficient, so that the particle swarm can be converged to a global optimal solution more quickly compared with the traditional particle swarm optimization.
Drawings
FIG. 1 is a schematic flow chart of a point of interest recommendation method based on a simulated annealing particle swarm algorithm according to an embodiment of the present invention;
FIG. 2 is another schematic flow chart of a point of interest recommendation method based on a simulated annealing particle swarm algorithm according to an embodiment of the present invention;
FIG. 3 is another schematic flow chart of a point of interest recommendation method based on a simulated annealing particle swarm algorithm according to an embodiment of the present invention;
FIG. 4 is another schematic flow chart of a point of interest recommendation method based on a simulated annealing particle swarm algorithm according to an embodiment of the present invention;
FIG. 5 is another schematic flow chart of a point of interest recommendation method based on a simulated annealing particle swarm algorithm according to an embodiment of the present invention;
FIG. 6 is another schematic flow chart of a method for recommending a point of interest based on a simulated annealing particle swarm algorithm according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of an algorithm convergence curve in the interest point recommendation method based on the simulated annealing particle swarm optimization provided by the embodiment of the invention;
FIG. 8 is a schematic diagram of a recommended interest point in the interest point recommendation method based on the simulated annealing particle swarm optimization according to the embodiment of the present invention;
fig. 9 is a schematic diagram of an attribute information list corresponding to each type of interest point set in the interest point recommendation method based on the simulated annealing particle swarm optimization provided in the embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided for illustrative purposes, and other advantages and effects of the present invention will become apparent to those skilled in the art from the present disclosure. While the invention will be described in conjunction with the preferred embodiments, it is not intended that features of the invention be limited to these embodiments. On the contrary, the invention is described in connection with the embodiments for the purpose of covering alternatives or modifications that may be extended based on the claims of the present invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. The invention may be practiced without these particulars. Moreover, some of the specific details have been left out of the description in order to avoid obscuring or obscuring the focus of the present invention. It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
It should be noted that in this specification, like reference numerals and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present embodiment, it should be noted that the terms "upper", "lower", "inner", "bottom", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings or orientations or positional relationships that are conventionally placed when the products of the present invention are used, and are only used for convenience in describing the present invention and simplifying the description, but do not indicate or imply that the devices or elements indicated must have specific orientations, be configured in specific orientations, and operate, and thus, should not be construed as limiting the present invention.
The terms "first," "second," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
In the description of the present embodiment, it should be further noted that, unless explicitly stated or limited otherwise, the terms "disposed," "connected," and "connected" are to be interpreted broadly, e.g., as a fixed connection, a detachable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. Specific meanings of the above terms in the present embodiment can be understood as specific cases by those of ordinary skill in the art.
To make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
In order to solve the problems that time consumption is long and multiple factors cannot be considered simultaneously in point of interest recommendation by using big data in the prior art, a particle swarm optimization algorithm is easy to fall into a local optimal solution, and accuracy of point of interest recommendation can be reduced, the embodiment provides a point of interest recommendation method based on a simulated annealing particle swarm algorithm. Specifically, referring to a flow diagram of an interest point recommendation method based on a simulated annealing particle swarm algorithm provided by an embodiment of the present invention shown in fig. 1, the interest point recommendation method based on the simulated annealing particle swarm algorithm provided by the embodiment specifically includes the following steps:
s1: generating an attribute information list corresponding to each type of interest point set according to the type of the interest point preselected by the user and the influence factors of the type of the interest point; each attribute information list comprises the number of each interest point in the interest point set of the corresponding type and interest point influence factors;
s2: establishing an expression of an optimization solution algorithm objective function aiming at all types of interest point sets;
s3: establishing initial particle swarm aiming at all types of interest point sets, and setting initial particle swarm parameters of a simulated annealing particle swarm algorithm for the initial particle swarm; the initial particle swarm parameters comprise the number of particles of the initial particle swarm, the preset iteration steps of the initial particle swarm and the dimensionality of each particle in the initial particle swarm, and the dimensionality of each particle in the initial particle swarm corresponds to the number of the types of the interest points preselected by the user;
s4: calculating and recording an initial objective function value and a corresponding particle position of each particle in the initial particle swarm, and a swarm objective function historical optimum value and a corresponding particle position of the initial particle swarm according to an expression of an optimization solution algorithm objective function;
s5: setting algorithm parameters of the simulated annealing particle swarm algorithm, and iteratively updating each particle in the initial particle swarm by utilizing the simulated annealing particle swarm algorithm according to the annealing algorithm parameters;
s6: calculating and recording the historical optimal value of the objective function of each particle and the corresponding particle position thereof in each generation of particle swarm after iterative update according to the expression of the objective function of the optimization solving algorithm, and the historical optimal value of the group objective function of each generation of particle swarm after iterative update and the corresponding particle position thereof; when the iteration step number of the updated particle swarm is equal to the preset iteration step number, ending the updating;
s7: and outputting the particles corresponding to the historical optimal value of the group objective function of the particle swarm, and taking the particles as recommended interest points.
By adopting the scheme, compared with the traditional recommendation algorithm based on big data, the method combining the simulated annealing algorithm and the particle swarm optimization is utilized, the problem of personalized recommendation of the interest points is solved, and the interest points are efficiently recommended on the premise of comprehensively considering multiple independent variable influence factors. Furthermore, in the iterative process of particle swarm optimization solution, a certain random probability is introduced by using the idea of a simulated annealing algorithm, and the annealing temperature is updated according to a preset proportion coefficient, so that the particle swarm can be converged to a global optimal solution more quickly compared with the traditional particle swarm optimization.
The method for recommending interest points based on the simulated annealing particle swarm algorithm provided by the embodiment is specifically described below with reference to fig. 1 to 9. Fig. 1 to 6 are schematic flow diagrams of a point of interest recommendation method based on a simulated annealing particle swarm algorithm according to an embodiment of the present invention; FIG. 7 is a schematic diagram of an algorithm convergence curve in the method for recommending interest points based on a simulated annealing particle swarm algorithm according to the embodiment of the present invention; FIG. 8 is a schematic diagram of a recommended interest point in the interest point recommendation method based on the simulated annealing particle swarm optimization according to the embodiment of the present invention; fig. 9 is a schematic diagram of an attribute information list corresponding to each type of interest point set in the interest point recommendation method based on the simulated annealing particle swarm optimization provided in the embodiment of the present invention.
Referring to fig. 1, firstly, step S1 is executed to generate an attribute information list corresponding to each type of interest point set according to the type of interest point preselected by the user and the influence factor of the type of interest point; each attribute information list comprises the number of each interest point in the interest point set of the corresponding type and the interest point influence factors.
Specifically, referring to fig. 2, in the present embodiment, step S1 includes:
s11: establishing an interest point list according to the type of interest points preselected by a user; wherein each interest point type comprises at least one interest point;
s12: and acquiring the influence factors of the interest point type.
It should be noted that, in this embodiment, the method for acquiring the influence factors of the user preselected interest point types includes:
and acquiring the influence factors of the type of the interest points preset by the user or acquiring the influence factors of the default type of the interest points.
S13: and acquiring attribute information of the interest point set of the corresponding type according to the influence factors of each interest point type, and generating an attribute information list.
It should be noted that, in this embodiment, the description is given by taking an example in which a user goes out and inputs an interest point to be experienced by using an intelligent cockpit system such as a central control screen, and then the intelligent cockpit system selects an optimal scheme according to the user's requirement.
Specifically, in step S1, the type of the point of interest preselected by the user may be a place that the user needs to traverse after going out and going home, which is specifically determined according to the need, for example, if the user needs to buy flowers, then go to eat, and finally go to a movie theater after going out, the type of the point of interest includes a flower shop, a restaurant, and a movie theater.
The influence factors of the interest point types are factors influencing the selection of the user when the user selects the interest points, such as average person consumption, waiting time, shop location and the like.
The interest point set is all shops which are selected by the system for the user and meet the conditions.
In an embodiment of the present invention, the user may select the interest points to be traversed according to the requirement, and the sequence of the interest points is the sequence of the stores to be traversed when the user travels. Assuming that the points of interest sequentially selected by the user are florists, restaurants and movie theaters, it is an overall process that the user starts from home and then goes home again.
After the user selects the interest points in sequence, the user creates an interest point list according to the selection of the user, as shown in fig. 9, and the interest point list only contains the numbers of shops, such as shop 1, shop 2, shop 3 … …, restaurant 1, restaurant 2, restaurant 3 … …, movie theater 1, movie theater 2, movie theater 3 … …
And then acquiring influence factors influencing the screening of the user in the interest point lists. It should be noted that these factors may be preset by the user or may be default by the system. Assume that the user presets influencing factors for selecting florists, restaurants, and movie theaters including store scores, average person consumption, store coordinates, and wait time. Of course, the user may set different influencing factors for different points of interest according to actual needs, which is not limited in this embodiment. In addition, in the embodiment, the influence factors such as the actual store score, per-person consumption, store coordinates, waiting time and the like of each store can be obtained through the third-party engine.
And then selecting some interest points in the interest point list according to the influence factors, and then generating an attribute information list. Reference may be made in particular to fig. 9. The attribute information list includes the number of the store and the influence factor.
Next, step S2 is executed to establish an expression of the optimization solution algorithm objective function for all types of interest point sets.
Specifically, referring to fig. 3, in the present embodiment, step S2 includes:
s21: respectively establishing a subfunction expression corresponding to each influence factor for each interest point type according to each influence factor of each interest point type;
s22: and performing summation operation on the subfunction expressions of all types of interest point sets to establish an expression of an optimization solution algorithm objective function.
It should be noted that, in this embodiment, an expression of an objective function of an optimization solution algorithm is established, that is, a function expression of each independent variable for an objective function value is respectively established for each interest point, and the function expressions of all the interest points that need to be traversed by one total process are cumulatively added to obtain the expression of the objective function of the optimization solution algorithm. The process of finding the best interest point is the process of solving the optimal solution (maximum or minimum) of the function expression. The numbers of the interest points of the types which are sequentially traversed and correspond to the optimal solution form an optimal interest point list recommended to the user.
It should be further noted that the step of constructing the expression of the objective function of the optimization solution algorithm specifically includes setting a reasonable objective function value, so that a function mapping relationship can be established between each independent variable and the objective function value, and the value is evaluated. Then, each independent variable (x1, (x2, y2), x3 and x4) of each interest point is subjected to function mapping to generate an evaluation value which can be uniformly measured. And acquiring the sum of the evaluation values of one total process (including n interest points needing to be traversed) of the user, namely the expression of the optimization solution algorithm objective function is Z ═ f1(x1) + f2(x2, y2) + f3(x3) + f4(x 4).
Specifically, in the present embodiment, the evaluation coefficient Z is set as an objective function value of an expression of the objective function. Z and the score of the third-party information engine on the jth POI in the ith class (x1)ij) The mapping relationship f1i of (c) is set as:where max is the maximum value for i.
The mapping f2 of Z to the position coordinates (x2, y2) of all the points of interest traversed (n are assumed) is set as: 0.6 × L. L is the kilometers of the total history, where 0.6 is the fuel consumption price per kilometer, and certainly, the fuel consumption price per kilometer is determined according to the actual situation, which is not specifically limited in this embodiment.
In the overall history, it is assumed that the position coordinate of the home is (0, 0), and the position coordinate of the jth interest point in the i-th class (i ═ 1 to n) in the traversal is (x 2)ij,y2ij) The calculation formula of the total course kilometers is as follows:
the mapping relationship f3i between Z and the per-person consumption (x3) of the ith interest point is set as follows: x3 (Yuan).
The expression of an overall history (including n interest points to be traversed) objective function of a user is as follows:
With continued reference to fig. 3, step S2 further includes:
s23: setting constraint conditions for each influence factor of the interest point type; wherein the constraint condition comprises an equality condition and an inequality condition.
The constraint condition set in step S23 is the f constraint in the expression of the objective function. The constraint of the equation, that is, the influencing factors (x1, x2, x3, x4) form an equation, such as x1+ x2 constant. The inequality constraint, that is, several influencing factors, form an inequality, such as x3+ x4< constant. For example, the constraint condition set by the user may be whether the user wants to wait at a certain type of interest point, and for different types of interest points, the user may set whether the user wants to wait, and if the user wants to wait, the user may set the maximum allowable waiting time.
In the embodiment of the invention, the user establishes the waiting time constraint conditions for the interest points of the florist and the restaurant, and the waiting time cannot exceed 15 minutes and 20 minutes respectively. When the waiting time t of the florist is greater than 15, f is restricted to ∞, otherwise 0. When the waiting time of the restaurant t is greater than 20, f is constraint ∞, otherwise 0.
Next, step S3 is executed, an initial particle swarm is established for all types of interest sets, and initial particle swarm parameters simulating the annealing particle swarm algorithm are set for the initial particle swarm; the initial particle swarm parameters comprise the number of particles of the initial particle swarm, the preset iteration steps of the initial particle swarm and the dimension of each particle in the initial particle swarm, and the dimension of each particle in the initial particle swarm corresponds to the number of the types of the interest points preselected by the user.
In this embodiment, in step S3, the establishing of the initial particle swarm for all types of interest sets includes:
s31: initializing particles in an initial particle swarm, and setting boundary conditions for the particles in the initial particle swarm;
s32: initializing an initialization velocity vector of particles in an initial particle swarm; wherein the initialization velocity vector is 0.5 to 0.7 times the initial value of the particle.
It should be noted that the initialized velocity vector is 0.5 to 0.7 times of the initial value of the particle, specifically, 0.5 times, 0.6 times, 0.7 times, or other values in this range, which is not limited in this embodiment.
In this embodiment, it is necessary to find the optimal solution of the expression of the objective function from the particle swarm. Therefore, in this step, an initial particle swarm needs to be established for all types of interest point sets to find the optimal value of the particle swarm, and then the optimal solution of the objective function is determined.
It should be noted that, in this embodiment, as shown in fig. 7, the preset iteration step number of the simulated annealing particle swarm algorithm is determined according to the calculation principle of the shortest time required for convergence.
In one embodiment of the present invention, one particle in one particle group is defined. Specifically, it is defined as (unidrnd (7), unidrnd (6), unidrnd (7)), where unidrnd (n) denotes that random integers between 1 and n are generated.
Each particle in the initial population of particles is then defined and parameters set. Specifically, when the dimension of each particle is set, the value of each dimension of the particle represents a list number (No.) selectable for the type of interest point. In other words, in this embodiment, each particle has three dimensions, which represent a florist, a restaurant, and a movie theater, respectively. When setting the initial velocity vector, the initial velocity vector value is set to 0.7 × for each particle (unidrnd (7), unidrnd (6), unidrnd (7)). When the initial particle number is set, the number of particles in the population is set. For example, the number of particles in the population is set to 20, and 20 particles are randomly generated, corresponding to 20 initial velocities. If the preset iteration step is set, the number of times that the particle swarm needs to be updated is set, and for example, the preset iteration step may be set to 10.
Next, step S4 is executed to calculate and record the initial objective function value and the corresponding particle position of each particle in the initial particle swarm, and the swarm objective function historical optimum value and the corresponding particle position of the initial particle swarm according to the expression of the objective function of the optimization solving algorithm.
In an embodiment of the invention, the historical optimal value p (1:20) of the objective function of 20 particles and the corresponding positions Y (1:20) of the particles are calculated and recorded according to the expression of the objective function of the optimization solution algorithm, and the historical optimal value Gbest of the objective function of the population and the corresponding particles are pg.
And then executing the step S5, setting the annealing algorithm parameters of the simulated annealing particle swarm algorithm, and iteratively updating each particle in the initial particle swarm by utilizing the simulated annealing particle swarm algorithm according to the annealing algorithm parameters.
In this embodiment, the annealing algorithm parameters include an initial annealing temperature, which is set to Wherein abs represents a pairAbsolute value processing is performed.
Specifically, referring to fig. 4, in this embodiment, iteratively updating each particle in each initial particle group by using a simulated annealing particle group algorithm according to the annealing algorithm parameter includes:
s51: calculating mutation probability of each particle according to an exponential probability formula, the current annealing temperature, the historical optimal value of the objective function of each particle and the historical optimal value of the group objective function of the particle swarm;
s52: determining the optimal particles in the contemporary particle group by using a roulette algorithm according to the distribution of the mutation probability;
s53: and moving each particle in each generation of particle swarm after iterative updating to a particle position corresponding to the target function historical optimal value of each particle and the optimal particle position in the current generation of particle swarm according to the self-learning rate, the swarm learning rate, the speed and speed inertial weight coefficient and the random rate between 0 and 1 so as to update each particle in each generation of particle swarm.
The mutation probability is the degree of approximation between the target function historical optimum value of each particle and the population target function historical optimum value of the particle group. The closer the two are, the greater the probability.
It should be noted that, in this embodiment, the exponential probability formula is:wherein p is the historical optimum value of the objective function of each particle; gbest is the historical optimum value of the population objective function of the particle swarm.
Preferably, in this embodiment, each particle in each particle group is updated according to the following formula:
Vk+1=C0*Vk+C1*rand*(Yk-Xk)+C2*rand*(Pgplus-Xk)
Xk+1=Xk+Vk+1
wherein the subscript k +1 represents the current iteration step number; v is the velocity vector of the particle; x is the current particle position; y is the particle position corresponding to the target function historical optimum value of the particle of the current particle; pgplusDetermining the optimal particles in the contemporary particle group by using a roulette algorithm under the contemporary iteration step number; c0Is a velocity inertial weight coefficient; generally, a random number between (0, 1) is taken. C1Is the self-learning rate of the particles; c2Is the population learning rate of the particle. c1, c2 are generally random numbers between (0, 2).
That is, in this embodiment, it is necessary to iteratively update the particles in the initial particle group, and select an optimal value for each generation. This process corresponds to a process of building a database and selecting an optimum value in the database. When the optimum particle in the particle group formed by the initial particle group and the updated particle group is determined by using the roulette algorithm, the particle having the higher mutation probability is more easily selected.
In this embodiment, referring to fig. 5, after step S5, the method further includes the following steps:
s5': judging whether each dimension value of each particle exceeds a boundary condition or not;
if yes, returning the particles exceeding the boundary condition to the boundary condition;
if not, step S6 is executed.
Specifically, whether the dimension of each particle exceeds the boundary condition is judged, and when the dimension exceeds the boundary condition, the particles exceeding the boundary condition are returned to the boundary condition. I.e. the dimensions of each particle X after the update are restricted not to exceed the specified boundary conditions. Out-of-condition particles recede into boundary conditions, i.e.Where Lb is the lower limit of the boundary condition and Ub is the upper limit of the boundary condition.
It should be noted that, in this embodiment, when updating the particle swarm, the particle swarm parameters may also be reset. For example, the moving speed of each particle of the present generation is set, and the like.
Then, step 6 is executed, the historical optimum value of the objective function of each particle and the corresponding particle position of each particle in each generation of particle swarm after iterative update are calculated and recorded according to the expression of the objective function of the optimization solving algorithm, and the historical optimum value of the group objective function of each generation of particle swarm after iterative update and the corresponding particle position of each group objective function; and when the iteration step number of the updated particle swarm is equal to the preset iteration step number, ending the updating.
Further, in this embodiment, after step S6, referring to fig. 6, the method further includes:
s6': and updating the annealing temperature according to the preset proportionality coefficient.
Specifically, in the present embodiment, the annealing temperature is updated according to the following formula: and T ═ T lambda, wherein T is the annealing temperature, and lambda is a preset proportionality coefficient.
It should be noted that the preset scaling factor may be defined according to the actual annealing condition, and in this embodiment, the preset scaling factor is a random number in a range of 0 to 1, and is preferably 0.4 to 0.7. Specifically, it may be 0.4, 0.5, 0.6, 0.7, or other values within the range.
S6': judging whether the number of the iteration steps is equal to a preset iteration step number or not;
if yes, ending the iteration and executing S7;
if not, entering the next iteration, and continuously judging whether the number of the iteration steps is equal to the preset number of the iteration steps.
After the iteration is finished, step S7 is executed to output the particle corresponding to the optimal value of the group objective function history of the particle swarm, and the particle is taken as the recommended interest point.
Specifically, referring to fig. 8, assuming that the particle pg corresponding to the optimal value of the objective function is [2, 2, 4], it represents that in this embodiment, pg is [2, 2, 4] is used as a recommendation list finally recommended to the user. That is, the user goes from home, sequentially traverses the flower shop numbered 2, the restaurant numbered 2, and the movie theater numbered 4, and then returns home.
Compared with the traditional recommendation algorithm based on big data, the recommendation method based on the simulated annealing algorithm and the particle swarm optimization solves the problem of personalized recommendation of the interest points, and realizes efficient recommendation of the interest points on the premise of comprehensively considering multi-independent variable influence factors. Furthermore, in the iterative process of particle swarm optimization solution, a certain random probability is introduced by using the idea of a simulated annealing algorithm, and the annealing temperature is updated according to a preset proportion coefficient, so that the particle swarm can be converged to a global optimal solution more quickly compared with the traditional particle swarm optimization.
While the invention has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that the foregoing is a more detailed description of the invention, taken in conjunction with the specific embodiments thereof, and that no limitation of the invention is intended thereby. Various changes in form and detail, including simple deductions or substitutions, may be made by those skilled in the art without departing from the spirit and scope of the invention.
Claims (10)
1. An interest point recommendation method based on a simulated annealing particle swarm algorithm is characterized by comprising the following steps of:
s1: generating an attribute information list corresponding to each type of interest point set according to the type of the interest point preselected by the user and the influence factors of the type of the interest point; each attribute information list comprises the number of each interest point in the interest point set of the corresponding type and interest point influence factors;
s2: establishing an expression of an optimization solution algorithm objective function aiming at all types of interest point sets;
s3: establishing an initial particle swarm for all types of interest point sets, and setting initial particle swarm parameters of a simulated annealing particle swarm algorithm for the initial particle swarm; wherein the initial particle swarm parameters comprise the number of particles of an initial particle swarm, a preset iteration step number of the initial particle swarm, and the dimension of each particle in the initial particle swarm corresponds to the number of the types of the points of interest preselected by the user;
s4: calculating and recording an initial objective function value and a corresponding particle position of each particle in the initial particle swarm, and a swarm objective function historical optimum value and a corresponding particle position of the initial particle swarm according to an expression of the optimization solution algorithm objective function;
s5: setting annealing algorithm parameters of the simulated annealing particle swarm algorithm, and iteratively updating each particle in the initial particle swarm by utilizing the simulated annealing particle swarm algorithm according to the annealing algorithm parameters;
s6: calculating and recording the historical optimal value of the objective function of each particle and the corresponding particle position thereof in each generation of particle swarm after iterative update according to the expression of the objective function of the optimization solving algorithm, and the historical optimal value of the group objective function of each generation of particle swarm after iterative update and the corresponding particle position thereof; when the iteration step number of the updated particle swarm is equal to the preset iteration step number, ending the updating;
s7: and outputting the particles corresponding to the historical optimal value of the group objective function of the particle swarm, and taking the particles as recommended interest points.
2. The method for recommending points of interest based on simulated annealing particle swarm optimization according to claim 1, wherein the step S1 comprises:
s11: establishing an interest point list according to the interest point types preselected by the user; wherein each of the interest point types comprises at least one interest point;
s12: acquiring influence factors of the interest point type;
s13: acquiring attribute information of the interest point set of the corresponding type according to the influence factors of each interest point type, and generating an attribute information list;
in step S12, the method for obtaining the influence factors of the point of interest type preselected by the user includes:
obtaining the influence factors of the interest point types preset by the user, or
And acquiring the default influence factors of the interest point type.
3. The method for recommending points of interest based on simulated annealing particle swarm optimization according to claim 2, wherein the step S2 comprises:
s21: respectively establishing a subfunction expression corresponding to each influence factor for each interest point type according to each influence factor of each interest point type;
s22: and performing summation operation on the subfunction expressions of the interest point sets of all types to establish an expression of an objective function of the optimization solution algorithm.
4. The method for recommending points of interest based on simulated annealing particle swarm optimization according to claim 3, wherein step S2 further comprises:
s23: setting constraint conditions for each influence factor of the interest point type; wherein the constraint condition comprises an equality condition and an inequality condition.
5. The method for recommending points of interest based on simulated annealing particle swarm optimization of claim 4, wherein in step S3, said establishing an initial particle swarm for all types of said set of points of interest comprises:
s31: initializing particles in the initial particle swarm and setting boundary conditions for the particles in the initial particle swarm;
s32: initializing an initialization velocity vector of particles in the initial particle swarm; wherein the initialization velocity vector is 0.5 to 0.7 times the initial value of the particle.
6. The method for recommending points of interest based on simulated annealing particle swarm optimization according to claim 5, wherein step S3 further comprises:
and determining the preset iteration step number of the simulated annealing particle swarm algorithm according to the calculation principle of the shortest time required by convergence.
7. The method for recommending points of interest based on simulated annealing particle swarm optimization of claim 6, wherein in step S5, said annealing algorithm parameters comprise an initial annealing temperature, said initial annealing temperature beingAnd the number of the first and second electrodes,
setting annealing algorithm parameters of the simulated annealing particle swarm algorithm, and iteratively updating each particle in the initial particle swarm by utilizing the simulated annealing particle swarm algorithm according to the annealing algorithm parameters comprises the following steps:
s51: calculating the mutation probability of each particle according to an exponential probability formula, the current annealing temperature, the historical optimal value of the objective function of each particle and the historical optimal value of the group objective function of the particle swarm; wherein the mutation probability is the approximation degree of the target function historical optimal value of each particle and the population target function historical optimal value of the particle swarm;
s52: determining the optimal particles in the contemporary particle group by using a roulette algorithm according to the distribution of the mutation probability;
s53: and moving each particle in each generation of particle swarm after iterative updating to a particle position corresponding to the target function historical optimal value of each particle and an optimal particle position in the current generation of particle swarm according to the self-learning rate, the swarm learning rate, the speed and speed inertial weight coefficient and the random rate between 0 and 1 so as to update each particle in each generation of particle swarm.
8. The method for recommending points of interest based on simulated annealing particle swarm optimization according to claim 7, wherein the exponential probability formula is:
wherein p is the historical optimum value of the objective function of each particle; gbest is a group objective function historical optimal value of the particle swarm; and is
Updating each particle in each particle population according to the following formula:
Vk+1=C0*Vk+C1*rand*(Yk-Xk)+C2*rand*(Pgplus-Xk)
Xk+1=Xk+Vk+1
wherein the subscript k +1 represents the current iteration step number; v is the velocity vector of the particle; x is the current particle position; y is the particle position corresponding to the target function historical optimum value of the particle of the current particle; pgplusDetermining the optimal particles in the contemporary particle group by using a roulette algorithm under the contemporary iteration step number; c0Is a velocity inertial weight coefficient; c1Is the self-learning rate of the particle; c2Is the population learning rate of the particle.
9. The method for recommending points of interest based on simulated annealing particle swarm optimization according to claim 8, further comprising the following steps after step S5:
s5': judging whether each dimension value of each particle exceeds the boundary condition or not;
if yes, returning the particles exceeding the boundary condition to the boundary condition;
if not, the step S6 is executed.
10. The method for recommending points of interest based on simulated annealing particle swarm optimization according to claim 9, further comprising, after step S6:
s6': updating the annealing temperature according to a preset proportionality coefficient; and, the annealing temperature is updated according to the following formula: t ═ T lambda, where T is the annealing temperature, lambda is the preset scaling factor, and the preset scaling factor ranges from 0 to 1 random number;
s6': judging whether the number of the iteration steps is equal to the preset iteration step number or not;
if yes, ending the iteration and executing S7;
if not, entering the next iteration.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011298454.3A CN114519135A (en) | 2020-11-19 | 2020-11-19 | Interest point recommendation method based on simulated annealing particle swarm algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011298454.3A CN114519135A (en) | 2020-11-19 | 2020-11-19 | Interest point recommendation method based on simulated annealing particle swarm algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114519135A true CN114519135A (en) | 2022-05-20 |
Family
ID=81595358
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011298454.3A Pending CN114519135A (en) | 2020-11-19 | 2020-11-19 | Interest point recommendation method based on simulated annealing particle swarm algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114519135A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116205536A (en) * | 2023-03-06 | 2023-06-02 | 阿里巴巴(中国)有限公司 | Object evaluation method, computing device, and readable storage medium |
CN116469527A (en) * | 2023-04-21 | 2023-07-21 | 脉景(杭州)健康管理有限公司 | Optimized recommendation method, system and equipment for traditional Chinese medicine prescription |
-
2020
- 2020-11-19 CN CN202011298454.3A patent/CN114519135A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116205536A (en) * | 2023-03-06 | 2023-06-02 | 阿里巴巴(中国)有限公司 | Object evaluation method, computing device, and readable storage medium |
CN116205536B (en) * | 2023-03-06 | 2023-10-13 | 阿里巴巴(中国)有限公司 | Object evaluation method, computing device, and readable storage medium |
CN116469527A (en) * | 2023-04-21 | 2023-07-21 | 脉景(杭州)健康管理有限公司 | Optimized recommendation method, system and equipment for traditional Chinese medicine prescription |
CN116469527B (en) * | 2023-04-21 | 2023-09-08 | 脉景(杭州)健康管理有限公司 | Optimized recommendation method, system and equipment for traditional Chinese medicine prescription |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105675002B (en) | A kind of more transit point navigation route planning method and systems | |
CN111240319B (en) | Outdoor multi-robot cooperative operation system and method thereof | |
CN107145161B (en) | Flight path planning method and device for unmanned aerial vehicle to access multiple target points | |
CN105469145B (en) | A kind of intelligent Auto-generating Test Paper method based on Genetic Particle Swarm Algorithm | |
Panda et al. | Evolutionary techniques for model order reduction of large scale linear systems | |
CN114519135A (en) | Interest point recommendation method based on simulated annealing particle swarm algorithm | |
CN116187896B (en) | Green vehicle path problem solving method, device, computer equipment and medium | |
CN112465439B (en) | Logistics distribution method and system based on intelligent brain control robot | |
CN110501020B (en) | Multi-target three-dimensional path planning method | |
CN111090899B (en) | Spatial layout design method for urban building | |
Lan et al. | Decomposition based multi-objective variable neighborhood descent algorithm for logistics dispatching | |
Emambocus et al. | An enhanced swap sequence-based particle swarm optimization algorithm to solve TSP | |
CN107609289A (en) | The building material cost management-control method and system of structural fortification based on BIM models | |
CN111178440B (en) | Path optimization method based on efficient reduction of total transport cost of AGV | |
CN106600959A (en) | Traffic congestion index-based prediction method | |
CN114897217A (en) | Fresh food electricity merchant front-end bin site selection-path planning method | |
Leng et al. | A multi-objective reinforcement learning approach for resequencing scheduling problems in automotive manufacturing systems | |
Li et al. | A mixing algorithm of ACO and ABC for solving path planning of mobile robot | |
US11308422B2 (en) | Method of and system for determining physical transfer interchange nodes | |
CN106600119A (en) | K-means-based power consumer clustering method and device | |
CN111178596A (en) | Logistics distribution route planning method and device and storage medium | |
Widayat et al. | Recommendations for Choosing a Place to Stay in the Greater Malang Area Using SAW and TOPSIS | |
CN109960762B (en) | Weather and time perception personalized POI sequence recommendation method | |
JP4364801B2 (en) | Area division system | |
CN115146866A (en) | Multi-equivalent optimal path planning method considering actual multi-constraints |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |