Bidding quotation simulation method and system

Abstract

The invention discloses a bidding quotation simulation method and system, and the method comprises the steps: initializing unknown quotation, which is used for randomly generating unknown quotation information according to known quotation information; wherein the known quotation information at least comprises an upper limit and a lower limit of quotation; wherein the randomly generated unknown quotation information at least comprises at least two randomly generated quotation information between the upper limit and the lower limit of the quotation; the quotation evaluation step is used for calculating the score of each quotation according to the known quotation information and the generated unknown quotation information; a neighborhood quotation obtaining step for finely adjusting the current quotation to generate a neighborhood quotation; and a simulated annealing algorithm step: continuously optimizing the quotation through the simulated annealing algorithm until the optimal quotation is found.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of artificial intelligence technology, and particularly relates to a bidding price simulation method and system. BACKGROUND

[0002] In the bidding process, bidding price is a very important link, and the rationality of bidding price directly affects the success of bidding. However, the bidding price methods in the current market mostly rely on artificial experience, and lack of scientificity and objectivity. Therefore, how to provide a scientific and objective bidding price simulation method and system has become a problem to be solved. SUMMARY

[0003] In order to solve the problem that the bidding price in the prior art mainly relies on experience, which may cause inaccurate bidding price, the purpose of the embodiments of the present disclosure is to provide a method and system for simulating bidding price by using artificial intelligence, so as to make the bidding price more accurate.

[0004] In order to achieve the above purpose, the embodiments of the present application provide a bidding price simulation method, comprising:

[0005] Step 1. Initialize the unknown price step, which is used to randomly generate unknown price information according to known price information; wherein the known price information at least includes: the upper limit and the lower limit of the price; wherein the randomly generated unknown price information at least includes: at least two price information randomly generated between the upper limit and the lower limit of the price;

[0006] Wherein the randomly generated unknown price information

[0007] x = random.uniform (lower_bound, upper_bound) ;

[0008] Wherein lower_bound and upper_bound are the lower limit and the upper limit of the price respectively;

[0009] Step 2. Evaluate the price step, which is used to calculate the score of each price according to the known price information and the generated unknown price information;

[0010] Step 3. Get the neighborhood price step, which is used to fine-tune the current price and generate neighborhood price; neighborhood price new_value = neighbor[index] + delta

[0011] Wherein, neighbor[index] is the previous price, and delta is the fine-tuning amount;

[0012] Step 4. Simulated annealing algorithm step, through the simulated annealing algorithm, the bid is constantly optimized until the optimal bid is found.

[0013] Further, in step 2, the score s of each current bid is calculated by the following formula:

[0014] s = 100 - 100 x n x m x abs(d);

[0015] Where d is the bid deviation (the difference between the bid price and the benchmark price, the benchmark price being the average of the current bid price), n and m are weight coefficients (the coefficients are provided by the tenderer or determined by experts); wherein the current bid includes: known bid information or randomly generated unknown bid information.

[0016] Further, step 4 includes:

[0017] Step 41. Initialize the current bid and the current score;

[0018] Step 42. Generate a neighborhood bid and calculate a neighborhood score;

[0019] 7. Step 43. Determine whether the neighborhood score is greater than the current score of the current bid; if so, update the current bid with the neighborhood bid, if the neighborhood score of the neighborhood bid is less than the current score for w consecutive times, the current bid is the optimal bid, and step 4 ends; if not, and the number of loops is less than the set value, return to step 42; if the number of loops is greater than the set value, step 4 ends.

[0020] Meanwhile, the embodiment of the present application proposes a bid simulation system, comprising:

[0021] An initialization module for randomly generating unknown bid information according to known bid information; wherein the known bid information at least includes: the upper limit and the lower limit of the bid; wherein the randomly generated unknown bid information at least includes: at least two bid information randomly generated between the upper limit and the lower limit of the bid;

[0022] Wherein the randomly generated unknown bid information

[0023] x = random.uniform(lower_bound, upper_bound);

[0024] Wherein lower_bound and upper_bound are the lower limit and the upper limit of the bid, respectively;

[0025] An evaluation module for calculating the score of each current bid according to the known bid information and the generated unknown bid information;

[0026] an optimization module for fine-tuning the current bid of the neighborhood module to generate a neighborhood bid, the neighborhood bid new_value = neighbor[index] + delta; wherein the neighbor[index] is the previous bid and the delta is the fine-tuning amount; and sending the neighborhood bid to the evaluation module to calculate a neighborhood score of the neighborhood bid, and continuously optimizing the bid according to the neighborhood score and the current score until the optimal bid is found;

[0027] outputting the optimal bid through the output module.

[0028] Further, the evaluation module calculates the score s of each current bid through the following formula:

[0029] s = 100 - 100 x n x m x abs(d);

[0030] wherein the d is the bid deviation, and the n and m are weight coefficients; wherein the current bid includes known bid information or randomly generated unknown bid information.

[0031] Further, the evaluation module is configured to perform the following steps:

[0032] Step 41. initializing the current bid and the current score;

[0033] Step 42. generating a neighborhood bid and calculating a neighborhood score;

[0034] Step 43. judging whether the neighborhood score is greater than the current score of the current bid; if yes, updating the current bid with the neighborhood bid, if the neighborhood scores of the neighborhood bids are all less than the current score for w consecutive times, the current bid is the optimal bid, and the step 4 is ended; if no, returning to the step 42.

[0035] The above technical solutions of the present application have the following beneficial effects: the scheme of the embodiment of the present application provides a scientific and objective bid simulation method and system, and improves the accuracy and efficiency of the bid. BRIEF DESCRIPTION OF DRAWINGS

[0036] The following drawings are used to provide further understanding of the present application, the illustrative examples of the present application and the description thereof are used to explain the present application, and do not constitute improper limitation on the present application. In the drawings:

[0037] Figure 1 is a flowchart of the bid simulation method of the embodiment of the present application;

[0038] Figure 2 is a logic diagram of the bid simulation system of the embodiment of the present application. DETAILED DESCRIPTION

[0039] It should be noted that the examples in the present application and the features in the examples can be combined with each other without conflict, unless specifically required, individual components and functions are optional, and the order of operation can be changed. Some parts and features of the embodiments can be included or replaced by parts and features of other embodiments. The scope of the embodiments of the present application includes the entire scope of the claims, and all available equivalents of the claims. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with examples.

[0040] According to an embodiment of the present application, a bidding simulation method is provided, comprising:

[0041] Step 1. Initialize the unknown bid step, for generating unknown bid information according to known bid information; wherein the known bid information at least includes: the upper limit and the lower limit of the bid; wherein the randomly generated unknown bid information at least includes: at least two bid information randomly generated between the upper limit and the lower limit of the bid;

[0042] Wherein, the randomly generated unknown bid information x = random.uniform(lower_bound, upper_bound); wherein lower_bound and upper_bound are the lower limit and the upper limit of the bid, respectively;

[0043] Step 2. Evaluate the bid step, for calculating the score of each bid according to the known bid information and the generated unknown bid information; wherein the

[0044] Specifically, the score s of each bid can be calculated by the following formula:

[0045] s = 100-100xnxmabs(d);

[0046] Wherein, d is the bid deviation, n and m are weight coefficients;

[0047] Step 3. Get the neighborhood bid step, for fine-tuning the current bid to generate the neighborhood bid; neighborhood bid new_value = neighbor[index] + delta

[0048] Wherein, delta is the fine-tuning amount;

[0049] Step 4. Simulated annealing algorithm step, through the simulated annealing algorithm, the bid is constantly optimized until the optimal bid is found;

[0050] Wherein, step 4 includes:

[0051] Step 41. Initialize the current bid and the current score;

[0052] Step 42. Generate a neighborhood offer and calculate a neighborhood score;

[0053] Step 43. Determine whether the neighborhood score is greater than the current score of the current offer; if yes, update the current offer with the neighborhood offer; if the neighborhood score of the neighborhood offer is less than the current score for w consecutive times, the current offer is the optimal offer, and step 4 ends; if no, return to step 42.

[0054] The technical solutions of the disclosure are further described below with a specific example:

[0055] Step 1. Initialize the unknown offer step, which is used to generate unknown offer information randomly according to known offer information when initializing the unknown offer; specifically, the unknown offer can be generated by the following formula:

[0056] x = random.uniform(lower_bound, upper_bound)

[0057] where lower_bound and upper_bound are the lower limit and upper limit of the offer, respectively;

[0058] Suppose the known offer information is {1: None, 2: None, 3: 1200, 4: 1400}, and the lower limit and upper limit of the offer are 1000 and 2000, respectively; the generated offer information 1 and 2 can be {1: 1100, 2: 1300, 3: 1200, 4: 1400};

[0059] Step 2. Evaluation offer step, which is used to calculate the score of each offer according to the known offer information and the generated unknown offer information when evaluating the offer. Specifically, the score can be calculated by the following formula:

[0060] s = 100 - 100 * n * m * abs(d);

[0061] In one possible implementation, the weight coefficients n and m can be set to 1 and 0.3, respectively, and the offer deviation d can be a range [-0.15, 0.10]; where d is the offer deviation, i.e., the difference between the bid offer and the benchmark price, and the benchmark price is the average of the current bid offer; n and m are weight coefficients, which can be provided by the tenderer or determined by experts;

[0062] Taking the example in step 1 as an example, the calculated score is {1: 90, 2: 95, 3: 100, 4: 100}; that is, the score of offer 1 is 90, the score of offer 2 is 95, the score of offer 3 is 100, and the score of offer 4 is 100;

[0063] Step 3. Obtain the neighborhood offer step, which is used to fine-tune the current offer to generate a neighborhood offer;

[0064] When obtaining the neighborhood offer, the current offer is fine-tuned to generate a neighborhood offer. Specifically, the neighborhood offer can be generated by the following formula:

[0065] new_value = neighbor[index] + delta

[0066] where delta is the fine-tuning amount;

[0067] The generated neighborhood offer is {1:1105,2:1305,3:1200,4:1400};

[0068] Step 4. Simulated annealing algorithm step, through the simulated annealing algorithm, the offer is constantly optimized until the optimal offer is found;

[0069] Wherein step 4 includes:

[0070] Step 41. Initialize the current offer and the current score;

[0071] Step 42. Generate a neighborhood offer and calculate the neighborhood score;

[0072] Step 43. Determine whether the neighborhood score is greater than the current score of the current offer; if so, update the current offer with the neighborhood offer, if the neighborhood score of the neighborhood offer is less than the current score for w consecutive times, the current offer is the optimal offer, and step 4 ends; if not, and the number of loops is less than the set value, return to step 42; if the number of loops is greater than the set value, step 4 ends.

[0073] Taking the above example as an example: assuming that the known offer information is {1:None,2:None,3:1200,4:1400}, the lower and upper limits of the offer are 1000 and 2000 respectively, the weight coefficients n and m are 1 and 0.3 respectively, and the deviation range is [-0.15, 0.10].

[0074] Step 1. Initialize the unknown offer step: according to the known offer information, randomly generate unknown offer information;

[0075] For example, generate the offer information as {1:1100,2:1300,3:1200,4:1400}.

[0076] Step 2. Evaluate the offer step: according to the known offer information and the generated unknown offer information, calculate the score of each offer.

[0077] For example, the calculated score is {1:90,2:95,3:100,4:100}.

[0078] Step 3. Obtain neighborhood offer step: fine-tune the current offer to generate a neighborhood offer;

[0079] For example, the generated neighborhood offer is {1:1105, 2:1305, 3:1200, 4:1400}.

[0080] Step 4. Simulated annealing algorithm step: constantly optimize the offer through the simulated annealing algorithm until the optimal offer is found;

[0081] For example, the generated offer information is {1:1100, 2:1300, 3:1200, 4:1400};

[0082] The neighborhood offer {1:1105, 2:1305, 3:1200, 4:1400} is generated, and the neighborhood score is calculated, for example, {1:97.87, 2:86.93, 3:96.03, 4:78.7};

[0083] Step 43. Determine whether the neighborhood score is greater than the current score of the current offer; if so, determine whether the neighborhood score is greater than the current score of the current offer; if so, update the current offer with the neighborhood offer, if the neighborhood score of the neighborhood offer is less than the current score for w consecutive times, the current offer is the optimal offer, and step 4 ends; if not, return to step 42;

[0084] With the aforementioned example, the current offer is {1:1100, 2:1300, 3:1200, 4:1400}, and the current score is {1:90, 2:95, 3:100, 4:100}; the generated neighborhood offer is {1:1105, 2:1305, 3:1200, 4:1400}; then according to step 4, after iterative calculation, the finally found optimal offer is {1:1150, 2:1350, 3:1200, 4:1400}.

[0085] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs. When the computer programs are loaded on a computer and executed, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer programs can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer programs can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (such as floppy disk, hard disk, magnetic tape), optical media (such as high-density digital video disc (digital video disc, DVD)), or semiconductor media (such as solid state disk (solid state disk, SSD)) and the like.

[0086] Those skilled in the art can understand that the first, second, etc. various numerical designations involved in the present application are only for the convenience of description, and do not limit the scope of the embodiments of the present application, nor indicate the order.

[0087] At least one of the present application can also be described as one or more, and the plurality can be two, three, four or more, which is not limited in the present application. In the embodiments of the present application, for a technical feature, the technical features in the technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D". There is no order or size order between the technical features described by "first", "second", "third", "A", "B", "C" and "D".

[0088] The correspondence relationship shown in each table in the present application can be configured or predefined. The values of the information in each table are merely examples, and other values can be configured, and the present application is not limited thereto. When configuring the correspondence relationship of the information and each parameter, it is not necessarily required to configure all the correspondence relationships shown in each table. For example, the correspondence relationship shown in some rows in the table in the present application can also not be configured. For another example, the above tables can be appropriately deformed, for example, split, merged, and the like. The names of the parameters shown in the titles of the above tables can also use other names understandable by the communication device, and the values or representation manners of the parameters can also use other values or representation manners understandable by the communication device. The above tables can also use other data structures when implemented, for example, an array, a queue, a container, a stack, a linear table, a pointer, a linked list, a tree, a graph, a structure, a class, a heap, a hash table, or the like.

[0089] The predefinition in the present application can be understood as defining, predefining, storing, pre-storing, pre-negotiating, pre-configuring, solidifying, or pre-burning.

[0090] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0091] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0092] The above is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A bidding and quotation simulation method, comprising: Step 1. Initializing unknown bid information, for randomly generating unknown bid information based on known bid information; wherein the known bid information includes at least an upper limit and a lower limit of the bid; wherein the randomly generated unknown bid information includes at least two randomly generated bid information located between the upper limit and the lower limit of the bid; Among them, the unknown quotation information is randomly generated x=random.uniform(lower_bound,upper_bound); Where lower_bound and upper_bound are the lower and upper limits of the quote respectively; Step 2: Evaluate the bids, which is used to calculate the score of each bid based on the known bid information and the generated unknown bid information. Step 3. Obtaining neighboring quotes, which is used to fine-tune the current quote and generate neighboring quotes; Neighbor quote new_value = neighbor[index] + delta Among them, neighbor[index] is the previous quote, and delta is the fine-tuning amount; Step 4. Simulated annealing algorithm step, through the simulated annealing algorithm, continuously optimize the quotation until the optimal quotation is found.

2. The bidding simulation method according to claim 1, wherein in step 2, the score s of each current bid is calculated by the following formula: s = 100 - 100 × n × m × abs(d); in, d is the bid deviation, which is the difference between the bid price and the benchmark price, where the benchmark price is the mean of the current bid prices; n and m are weight coefficients; The current quotation includes: known quotation information or randomly generated unknown quotation information.

3. The bidding and quotation simulation method according to claim 1, wherein step 4 comprises: Step 41. Initialize the current quote and current score; Step 42: Generate neighborhood quotes and calculate neighborhood scores. Step 43: Determine whether the neighborhood score is greater than the current score of the current bid; If yes, the current quotation is updated using the domain quotation. If the neighborhood scores of w consecutive domain quotations are all less than the current score, the current quotation is the optimal quotation and step 4 ends. If no, and the number of loops is less than the set value, return to step 42. If the number of loops is greater than the set value, step 4 ends.

4. A bidding and quotation simulation system, comprising: An initialization module is configured to randomly generate unknown quotation information based on known quotation information; wherein the known quotation information includes at least an upper limit and a lower limit of the quotation; wherein the randomly generated unknown quotation information includes at least two randomly generated quotation information located between the upper limit and the lower limit of the quotation; Among them, the unknown quotation information is randomly generated x=random.uniform(lower_bound,upper_bound); Where lower_bound and upper_bound are the lower and upper limits of the quote respectively; An evaluation module, used to calculate the score of each current quotation based on known quotation information and generated unknown quotation information; The optimization module is used to fine-tune the current quotation of the neighborhood module and generate a neighborhood quotation, where the neighborhood quotation new_value = neighbor[index] + delta; where neighbor[index] is the previous quotation and delta is the fine-tuning amount; and the neighborhood quotation is sent to the evaluation module to calculate the neighborhood score of the neighborhood quotation. Based on the neighborhood score and the current score, the quotation is continuously optimized until the optimal quotation is found. Output the best quotation through the output module.

5. The bidding simulation system according to claim 4, wherein the evaluation module calculates the score s of each current bid using the following formula: s = 100 - 100 × n × m × abs(d); in, d is the quotation deviation, n and m are weight coefficients; the current quotation includes: known quotation information or randomly generated unknown quotation information.

6. The bidding and quotation simulation system according to claim 1, wherein the evaluation module is configured to perform the following steps: Step 41. Initialize the current quote and current score; Step 42: Generate neighborhood quotes and calculate neighborhood scores. Step 43: Determine whether the neighborhood score is greater than the current score of the current bid; If yes, the current quotation is updated with the domain quotation. If the neighborhood scores of w consecutive domain quotations are all smaller than the current score, the current quotation is the optimal quotation and step 4 ends; otherwise, return to step 42.

Images