CN111192161A - Electric power market trading object recommendation method and device - Google Patents
Electric power market trading object recommendation method and device Download PDFInfo
- Publication number
- CN111192161A CN111192161A CN201911319548.1A CN201911319548A CN111192161A CN 111192161 A CN111192161 A CN 111192161A CN 201911319548 A CN201911319548 A CN 201911319548A CN 111192161 A CN111192161 A CN 111192161A
- Authority
- CN
- China
- Prior art keywords
- user
- recommended
- electric power
- users
- power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000005611 electricity Effects 0.000 claims abstract description 78
- 238000004364 calculation method Methods 0.000 claims abstract description 28
- 239000013598 vector Substances 0.000 claims abstract description 18
- 238000012216 screening Methods 0.000 claims abstract description 15
- 230000006399 behavior Effects 0.000 claims description 23
- 230000002146 bilateral effect Effects 0.000 claims description 20
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 5
- 239000002699 waste material Substances 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Computational Biology (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a device for recommending electric power market trading objects, wherein the recommending method comprises the following steps: establishing a power purchase user model according to the user behavior data, acquiring the weight of each attribute element in the user behavior data, and representing the power purchase user model by adopting a vector space model; the method comprises the steps of obtaining information of a user to be recommended, carrying out similarity calculation on the user to be recommended and the rest users in an electricity purchasing user model according to the information to obtain a recommending unit list and purchasing frequency, and carrying out similarity calculation according to electric power data to obtain a user set of the user to be recommended; and generating a final recommendation list for the user to be recommended to select, wherein the final recommendation list comprises the user set, the recommended power plant list and the purchase frequency. The method and the system can recommend the machine set and the user set suitable for the electricity purchasing users for different electricity purchasing users, are convenient for the users to quickly select the suitable transaction objects, avoid financial waste, do not need to spend time for screening, have high efficiency and reduce the labor cost.
Description
Technical Field
The invention relates to the technical field of power grids, in particular to a method and a device for recommending electric power market trading objects.
Background
With the rapid development of social economy in China, the demand of people on power consumption is more and more, and the development of the electric power market is further promoted to the maximum extent. Under the new situation, the economic system reformation is continuously deepened, which also leads the electric power system reformation to speed up the pace, and finally leads the competition of the electric power market to be increasingly fierce.
In order to open the electric power market, the existing electric power selling mechanism provides an electric power trading mode of directly trading a power plant and an electric power purchasing user, wherein the power plant directly purchases electric power. However, in the electric power market, the number of power plants as transaction targets is large, and the voltage class of the electricity purchasing party and the industry where the electricity purchasing party is located are different, so that the transaction targets suitable for different electricity purchasing users are different. When facing a plurality of power plants, the method is difficult to select a proper transaction object according to the self condition, is easy to select errors, wastes financial resources of electricity purchasing users, often needs to screen for a large amount of time when carrying out electric power transaction, and has low efficiency and high labor cost.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides the method and the device for recommending the trading objects in the power market, which can be used for recommending the machine set suitable for the electricity purchasing users and the user set similar to the electricity purchasing users for different electricity purchasing users by performing similarity calculation according to user behavior data, are convenient for the users to quickly select the suitable trading objects, avoid financial resource waste, do not need to consume time for screening, have high efficiency and reduce the labor cost.
In order to solve the above problems, the present invention adopts a technical solution as follows: a recommendation method for trading objects in an electric power market comprises the following steps of; s101: establishing a power purchase user model according to user behavior data, acquiring the weight of each attribute element in the user behavior data, and representing the power purchase user model by adopting a vector space model; s102: obtaining information of a user to be recommended, calculating the similarity between the user to be recommended and the rest users in the electricity purchasing user model according to the information to obtain a recommending unit list and purchasing frequency, and calculating the similarity according to electric power data to obtain a user set of the user to be recommended; s103: generating a final recommendation list for the user to be recommended to select, wherein the final recommendation list comprises a user set, a list of recommended power plants and a purchase frequency.
Further, the user behavior data includes: the system comprises power consumer basic attributes, power seller basic attributes, current contract attributes and power consumption attributes.
Further, the user behavior data comprise electric quantity data, and deviation electric quantity calculation is carried out in a fuzzy comprehensive evaluation-based mode to obtain the electric quantity data.
Further, the step of representing the electricity purchasing user model by using the vector-based space model specifically includes: and representing each attribute element and the weight thereof by a vector, and representing the electricity purchasing user model by an n-dimensional vector space.
Further, the step of calculating the similarity between the user to be recommended and the remaining users in the electricity purchasing user model according to the information to obtain a recommended unit list and a purchasing frequency specifically includes: calculating the similarity between the user to be recommended and the rest users to obtain users with similarity sequencing within a preset range; acquiring a unit set corresponding to the user, and screening out units with tradeable electric quantity smaller than a first preset value from the unit set; and sorting the units in the unit set according to the proportion of the purchased electric quantity, and generating a recommended unit list and purchase frequency according to the sorting.
Further, the power data includes monthly bilateral contract power, monthly bilateral contract power price, monthly bilateral total power charge, monthly total power, yearly bilateral total power charge, and yearly bilateral total power charge.
Further, before the step of obtaining the user set of the users to be recommended by performing similarity calculation according to the power data, the method further includes: acquiring the voltage grade of the user to be recommended, and screening out a user set with the same voltage grade from the electricity purchasing user model; and screening users with the same industry grades as the users to be recommended from the user set.
Further, the step of performing similarity calculation according to the power data to obtain the user set of the user to be recommended specifically includes: and according to the electric power data, similarity calculation is carried out on the user to be recommended and the user which is classified at each level and is the same as the user to be recommended, and similarity sequencing is carried out to generate a user set.
Further, the step of generating a final recommendation list for the user to be recommended to select specifically includes: and acquiring the weight of the user according to the position information of the user in the user set, and weighting the user set to generate the final recommendation list.
Based on the same inventive concept, the invention also provides an electric power market trading object recommendation device, which comprises a processor and a memory, wherein the processor is coupled with the memory; the memory stores program data, and the processor executes the electric power market trading object recommendation method according to the program data.
Compared with the prior art, the invention has the beneficial effects that: the method and the device can carry out similarity calculation according to the user behavior data to recommend the machine set suitable for the electricity purchasing users and the user set similar to the electricity purchasing users for different electricity purchasing users, so that the users can quickly select the suitable transaction objects, financial resources are avoided being wasted, time screening is not needed, the efficiency is high, and the labor cost is reduced.
Drawings
FIG. 1 is a flowchart illustrating an embodiment of a method for recommending an electric power market trading object according to the present invention;
FIG. 2 is a flowchart illustrating an embodiment of obtaining a unit recommendation list and a purchase frequency in the method for recommending an electric power market trading object according to the present invention;
FIG. 3 is a flowchart illustrating an embodiment of obtaining a user set according to the method for recommending an electric power market trading object of the present invention;
FIG. 4 is a diagram illustrating a structure of a location model according to an embodiment of the method for recommending an electric power market trading object;
FIG. 5 is a flowchart illustrating an embodiment of generating a final recommendation list in the method for recommending an electricity market trading object according to the present invention;
FIG. 6 is a block diagram of an embodiment of industry grading in the method for recommending an object for a power market trading according to the present invention;
fig. 7 is a structural diagram of an embodiment of the electric power market trading object recommendation device of the present invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and the detailed description, and it should be noted that any combination of the embodiments or technical features described below can be used to form a new embodiment without conflict.
Referring to fig. 1-6, fig. 1 is a flowchart illustrating a method for recommending an electric power market trading object according to an embodiment of the present invention; FIG. 2 is a flowchart illustrating an embodiment of obtaining a unit recommendation list and a purchase frequency in the method for recommending an electric power market trading object according to the present invention; FIG. 3 is a flowchart illustrating an embodiment of obtaining a user set according to the method for recommending an electric power market trading object of the present invention; FIG. 4 is a diagram illustrating a structure of a location model according to an embodiment of the method for recommending an electric power market trading object; FIG. 5 is a flowchart illustrating an embodiment of generating a final recommendation list in the method for recommending an electricity market trading object according to the present invention; fig. 6 is a structural diagram of an embodiment of industry grading in the method for recommending an electric power market trading object according to the present invention. The electric power market trading object recommendation method of the invention is explained in detail with reference to the accompanying drawings 1-6.
In this embodiment, the electric power market trading object recommendation method includes:
s101: and constructing a power purchase user model according to the user behavior data, acquiring the weight of each attribute element in the user behavior data, and representing the power purchase user model by adopting a vector space model-based representation method.
In this embodiment, the user behavior data includes: the system comprises power consumer basic attributes, power seller basic attributes, current contract attributes and power consumption attributes.
In this embodiment, the device for executing the electric power market trading object recommendation method may be a cloud platform, a server, a computer, and other electric power selling platforms or terminals.
The basic attributes of the power users comprise attribute element information which represents the identity attribute of the power users, such as user numbers, user names, industries, regions, voltage levels, self-contained power plants and the like; the basic attributes of the electricity selling parties comprise attribute elements representing identity identification attributes of the electricity selling parties, such as a unit number, the name of the electricity selling party to which the unit belongs, tradable electricity quantity, unit capacity, planned electricity quantity, plant electricity consumption rate, bilateral electricity quantity, long-term electricity quantity and the like; the contract attributes include: attribute elements related to specific information of the current contract of the power consumer, such as contract number, contract identification, user number, power consumer name, unit number, unit name, contract start date, contract end date, contract period, contract electric quantity, contract price and the like; the power consumption attributes comprise attribute elements related to actually consumed power amount information, such as user numbers, trading months, monthly contract electric quantity, monthly total electric charge, monthly total electric quantity, self-contained power plant generated energy and the like.
In this embodiment, the purchasing behavior of the user is refined by calculating similarities through attribute elements such as monthly bilateral contract electricity quantity, monthly bilateral contract electricity price, monthly bilateral total electricity charge, annual bilateral total electricity charge (reduced to months), monthly centralized bidding electricity quantity, monthly centralized bidding total electricity quantity, monthly total electricity charge and the like, and weights of the attribute elements, so as to form sufficient analyzable data.
In this embodiment, the weight of the attribute element may be stored in the device for executing the power market trading recommendation method in advance, or may be input when the power purchase user model is established, which is not limited herein.
In the embodiment, the collaborative filtering algorithm of the user is adopted to calculate the similarity, rather than the collaborative filtering algorithm based on the articles, mainly because the collaborative filtering algorithm is suitable for the items with a small number of users, otherwise, the cost for calculating the similarity of the user is huge, and the collaborative filtering algorithm is also very suitable for the scene where the preference of the user is not very obvious.
In the embodiment, the user behavior data comprises electric quantity data, and in order to further improve the accuracy of the electric quantity data, when the electric quantity is calculated, a fuzzy comprehensive evaluation-based method is added to calculate the deviation electric quantity to provide more accurate electric quantity data, so that the electric quantity data obtained by feedback is more accurate.
The existing deviation electric quantity processing methods have certain limitations. In view of the fact that at present, no mature deviation electric quantity pricing mechanism and responsibility judgment mechanism exist in China, the invention provides a new method for processing the deviation electric quantity of the transaction settlement according to the idea that all transaction components participating in the transaction settlement share and quantitatively bear deviation and under the influence of 4 factors of the transaction type, the transaction period transaction electric quantity and the transaction electricity price of the transaction components.
The method mainly comprises the following two steps: firstly, constructing a settlement component index model based on fuzzy comprehensive evaluation, wherein two factors of transaction type and transaction period belong to qualitative indexes, and acquiring a membership function by using an analytic hierarchy process in combination with working practice; the two factors of the transaction electric quantity and the transaction price belong to quantitative indexes, and the result of linear normalization by directly adopting the specific numerical value of the transaction component is used as a membership function. And secondly, constructing a deviation electric quantity settlement model based on settlement component indexes, and taking a fuzzy comprehensive evaluation result as a basis for distributing the deviation electric quantity. More accurate electric quantity data can be obtained through the deviation calculation. And finally, the recommendation result is more accurate.
In the embodiment, the electricity purchasing user model is represented by a vector space model-based representation method. The representation method specifically comprises the following steps: and representing the attribute elements and the weights thereof by vectors, and representing the electricity purchasing user model by an n-dimensional vector space. Each vector comprises a keyword and a weight of an attribute element, the name of the attribute element is used as the keyword of the vector, the vector space is identified by (tl, wl), (t2, w2),.. (tn, wn), t1, t2 … tn are the keywords, and w1, w2 … wn are the weights. The method for representing the electricity purchasing user model by using the vector space model can refer to the prior art, and is not described herein again.
The expression method of the vector space model is favorable for matching the requirements of the electricity purchasing users, and the model is better in expression because the electricity purchasing users do not score the transaction objects.
S102: the method comprises the steps of obtaining information of a user to be recommended, carrying out similarity calculation on the user to be recommended and the rest users in an electricity purchasing user model according to the information to obtain a recommending unit list and purchasing frequency, and carrying out similarity calculation according to electric power data to obtain a user set of the user to be recommended.
In this embodiment, the step of calculating the similarity between the user to be recommended and the remaining users in the electricity purchasing user model according to the information to obtain the list of recommended units and the purchasing frequency specifically includes: calculating the similarity of the user to be recommended and the rest users to obtain users with similarity in a preset range; acquiring a set corresponding to a user, and screening out the set with the tradable electric quantity smaller than a first preset value from the set; and sorting the units in the unit set according to the proportion of the purchased electric quantity, and generating a recommended unit list and purchase frequency according to the sorting.
In an embodiment, the user to be recommended may be generated according to access and login conditions of the electricity purchasing user, may also be generated according to a query instruction of the electricity purchasing user, and may also be generated according to information of the electricity purchasing user input by the user, which is not limited herein.
In this embodiment, the preset range is 5 items before the similarity ranking, the first preset value is 5% of the capacity of the unit, in other embodiments, the preset range and the first preset value may also be other values, and the user may set the preset range and the first preset value according to the own needs and actual situations, which is not limited herein.
In a specific embodiment, an electricity purchasing user model is generated according to original user behavior data, a user to be recommended is determined, similarity calculation is performed on the user to be recommended and all remaining users (users to be matched) to obtain primary similarity, and the user similarity is ranked. And extracting the top 5 users with the similarity, and extracting the machine set corresponding to the historical electricity purchasing of the top five users in the electricity purchasing behavior data of the users to form a machine set. And screening out the units with the tradable electric quantity less than 5% of the unit capacity from the unit set, sequencing the rest units in the unit set according to the proportion of the purchased electric quantity to generate a unit recommendation list, and acquiring the purchase frequency of the units according to the historical electricity purchase data of the units.
In this embodiment, when performing similarity calculation, examples of the similarity calculation method that can be used include a Jaccard similarity coefficient, a cosine similarity, an euclidean distance, a mahalanobis distance, and other similarity calculation methods.
In a preferred embodiment, the Mahalanobis distance is adopted for similarity calculation, and the Mahalanobis distance is used as a variance matrix, so that the variances among all components in the electricity purchasing user model are eliminated, the dimension is eliminated, and the method is more scientific and reasonable.
In this embodiment, the power data includes monthly bilateral contract power, monthly bilateral contract power rate, monthly bilateral total power rate, monthly total power rate, yearly bilateral total power rate, and yearly bilateral total power rate. And performing similarity calculation according to the power data to obtain a user set.
In this embodiment, a user set having a certain similarity with a user to be recommended is searched through a power purchase user model; and searching a transaction object which generates a transaction with the user and does not generate a transaction with the electricity purchasing user in the user set, and recommending the transaction object to the electricity purchasing user.
In this embodiment, before the step of obtaining the user set of the users to be recommended by performing similarity calculation according to the power data, the method further includes: obtaining the voltage grade of a user to be recommended, and screening out a user set with the same voltage grade from the electricity purchasing user model; and screening users with the same industry grades as the users to be recommended from the user set.
In this embodiment, three levels of classifications (level 0, level 1, and level 2) of an industry where a user to be recommended is located are obtained, users that are the same as at least one level of classification of the three levels of classifications are selected from a user set, and users similar to the user to be recommended are screened from the users.
In this embodiment, the step of performing similarity calculation according to the power data to obtain the user set of the to-be-recommended users specifically includes: and according to the electric power data, similarity calculation is carried out on the user to be recommended and the user with the same classification of each level and the user to be recommended, and similarity sequencing is carried out to generate a user set.
In this embodiment, the input information of the user to be recommended is received, the voltage level of the user to be recommended is searched according to the information, and the user with the same voltage level as the user to be recommended is screened out from the electricity purchasing user model. Searching three-level classification (level 0, level 1 and level 2) of the industry where the user to be recommended is located, extracting all the users of the level 0 classification where the user to be recommended is located, and calculating similarity of monthly contract electric quantity, contract electricity price (unit price), monthly total electricity charge and monthly total electric quantity data by using the Mahalanobis distance according to the user to be recommended and the user of the level 0. And carrying out similarity sorting according to the calculation result. And extracting all class-1 users where the users to be recommended are located, calculating the similarity of monthly contract electric quantity, contract electricity price (unit price), monthly total electricity charge and monthly total electric quantity data by using the Mahalanobis distance according to the users to be recommended and the class-1 users where the users to be recommended are located, and sequencing the similarity according to the calculation result. Extracting all class-2 users where the users to be recommended are located, calculating similarity of monthly contract electric quantity, contract electricity price (unit price), monthly total electricity charge and monthly total electric quantity data by using the Mahalanobis distance according to the class-2 users where the users to be recommended are located, and sequencing the similarity according to the calculation result. And obtaining similar users with similarity ranks in a first preset range according to the similarity ranks of different levels of classifications, and forming a user set according to the similar users. The size of the first preset range may be set according to a user requirement, and is not limited herein.
In a specific embodiment, the electricity purchasing user is a food manufacturing industry, a recommended user list is firstly generated according to data (similarity is calculated by using mahalanobis distance) of all users, then a second recommended user list is generated by using all users of the manufacturing industry, and then a third recommended user list is generated for all users of the food manufacturing industry. Then, the 3 recommended user lists are multiplied by the respective weights and added to obtain a final recommended user list for the user.
S103: and generating a final recommendation list for the user to be recommended to select, wherein the final recommendation list comprises the user set, the recommended power plant list and the purchase frequency.
In this embodiment, the step of generating the final recommendation list for the user to be recommended to select specifically includes: and acquiring the weight of the user according to the position information of the user in the user set, and weighting the user set to generate a final recommendation list.
In the embodiment, since the context information of the electricity purchasing user is ignored, a certain deviation is easily generated in the recommendation result, and therefore, in the invention, the position information is further arranged for concatenation, and the recommendation effect is improved. And forming a position model through position information in the user behavior data, and generating a recommendation list for the user on each intermediate node from the root node to the sub-leaf node in the position model according to the information of the user included by the node. And the final recommendation is a weighting of these recommendation lists.
In the above embodiment, the order of forming the recommendation list according to the location information and the industry information of the user may be freely set, the recommendation list may be formed according to industry classification first, then the users in the recommendation list are screened according to the location information, or the users may be screened according to the location information first and then the industry classification, or one of the industry classification and the location information may be selected to screen users similar to the electricity purchasing user, which is not limited herein.
In a specific embodiment, a user to be recommended belongs to prefecture, a city, B prefecture, a certain province, a recommendation list 1 is generated according to all user behavior data of the prefecture, a recommendation list 2 is generated according to all user behavior data of city, a recommendation list 3 is generated according to all user behavior data of prefecture, the recommendation list 1 is multiplied by weight a, the recommendation list 2 is multiplied by weight B, the recommendation list 3 is multiplied by weight c, and the recommendation lists multiplied by the weights are added to form a final recommendation list.
Has the advantages that: the method and the device can be used for carrying out similarity calculation according to the user behavior data to recommend the machine set suitable for the electricity purchasing user and the user set similar to the electricity purchasing user for different electricity purchasing users, so that the users can quickly select the suitable transaction object, financial resources are avoided being wasted, time screening is not needed, the efficiency is high, and the labor cost is reduced.
Based on the same inventive concept, the present invention further provides an electric power market trading object recommendation device, please refer to fig. 7, fig. 7 is a structural diagram of an embodiment of the electric power market trading object recommendation device of the present invention, and the electric power market trading object recommendation device of the present invention is specifically described with reference to fig. 7.
In this embodiment, the electric power market trading object recommendation device comprises a processor and a memory, wherein the processor is coupled with the memory; the memory stores program data, and the processor executes the electric power market trading object recommendation method according to the embodiment.
In this embodiment, the electric power market transaction recommendation device may be a cloud platform, a server, a computer, and other electric power selling platforms or terminals.
Has the advantages that: the electric power market trading object recommending device can be used for recommending the machine set suitable for the electricity purchasing users and the user set similar to the electricity purchasing users for different electricity purchasing users by performing similarity calculation according to the user behavior data, so that the users can quickly select the suitable trading objects, financial resources are avoided being wasted, time-consuming screening is not needed, the efficiency is high, and the labor cost is reduced.
The above embodiments are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby, and any insubstantial changes and substitutions made by those skilled in the art based on the present invention are within the protection scope of the present invention.
Claims (10)
1. A recommendation method for trading objects in an electric power market is characterized by comprising the following steps of;
s101: establishing a power purchase user model according to user behavior data, acquiring the weight of each attribute element in the user behavior data, and representing the power purchase user model by adopting a vector space model;
s102: obtaining information of a user to be recommended, calculating the similarity between the user to be recommended and the rest users in the electricity purchasing user model according to the information to obtain a recommending unit list and purchasing frequency, and calculating the similarity according to electric power data to obtain a user set of the user to be recommended;
s103: generating a final recommendation list for the user to be recommended to select, wherein the final recommendation list comprises a user set, a list of recommended power plants and a purchase frequency.
2. The power market trading object recommendation method of claim 1, wherein the user behavior data comprises: the system comprises power consumer basic attributes, power seller basic attributes, current contract attributes and power consumption attributes.
3. The electric power market trading object recommendation method of claim 1, wherein the user behavior data comprises electric quantity data, and the electric quantity data is obtained by calculating deviation electric quantity based on fuzzy comprehensive evaluation.
4. The method for recommending an object for trading in an electric power market according to claim 1, wherein said step of representing said electricity purchasing user model based on a vector space model specifically comprises:
and representing each attribute element and the weight thereof by a vector, and representing the electricity purchasing user model by an n-dimensional vector space.
5. The method for recommending electricity market trading objects according to claim 1, wherein the step of calculating the similarity between the user to be recommended and the remaining users in the electricity purchasing user model according to the information to obtain the list of recommended units and the purchasing frequency specifically comprises:
calculating the similarity between the user to be recommended and the rest users to obtain users with similarity sequencing within a preset range;
acquiring a unit set corresponding to the user, and screening out units with tradeable electric quantity smaller than a first preset value from the unit set;
and sorting the units in the unit set according to the proportion of the purchased electric quantity, and generating a recommended unit list and purchase frequency according to the sorting.
6. The electric power market trading object recommendation method of claim 1, wherein the electric power data comprises monthly bilateral contract electric power amount, monthly bilateral contract electric power price, monthly bilateral total electric power charge, monthly total electric power amount, yearly bilateral total electric power charge, and yearly bilateral total electric power charge.
7. The method for recommending an electricity market trading object according to claim 6, wherein the step of obtaining the user set of the users to be recommended by performing similarity calculation according to the electricity data further comprises:
acquiring the voltage grade of the user to be recommended, and screening out a user set with the same voltage grade from the electricity purchasing user model;
and screening users with the same industry grades as the users to be recommended from the user set.
8. The method for recommending power market trading objects according to claim 7, wherein the step of performing similarity calculation according to power data to obtain the user set of the users to be recommended specifically comprises:
and according to the electric power data, similarity calculation is carried out on the user to be recommended and the user which is classified at each level and is the same as the user to be recommended, and similarity sequencing is carried out to generate a user set.
9. The power market trading object recommendation method of claim 1, wherein the step of generating a final recommendation list for selection by the user to be recommended specifically comprises:
and acquiring the weight of the user according to the position information of the user in the user set, and weighting the user set to generate the final recommendation list.
10. An electric power market trading object recommendation device is characterized by comprising a processor and a memory, wherein the processor is coupled with the memory;
the memory stores program data according to which the processor executes the electric power market trading object recommendation method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911319548.1A CN111192161A (en) | 2019-12-19 | 2019-12-19 | Electric power market trading object recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911319548.1A CN111192161A (en) | 2019-12-19 | 2019-12-19 | Electric power market trading object recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111192161A true CN111192161A (en) | 2020-05-22 |
Family
ID=70709241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911319548.1A Pending CN111192161A (en) | 2019-12-19 | 2019-12-19 | Electric power market trading object recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111192161A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111858686A (en) * | 2020-07-08 | 2020-10-30 | 深圳市富途网络科技有限公司 | Data display method and device, terminal equipment and storage medium |
| CN115601195A (en) * | 2022-10-17 | 2023-01-13 | 桂林电子科技大学（Cn） | Transaction bidirectional recommendation system and method based on real-time label of power user |
| CN116707019A (en) * | 2023-05-12 | 2023-09-05 | 云南电网有限责任公司信息中心 | Electric quantity distribution method, system and computer equipment for daily electric power market |
| CN117273870A (en) * | 2023-11-22 | 2023-12-22 | 北京清众神州大数据有限公司 | Auxiliary decision-making method, device, equipment and storage medium for electric power market transaction |
| CN111858686B (en) * | 2020-07-08 | 2024-05-28 | 深圳市富途网络科技有限公司 | Data display method, device, terminal equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095256A (en) * | 2014-05-07 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Information push method and apparatus based on similarity degree between users |
| CN106933821A (en) * | 2015-12-29 | 2017-07-07 | 中国电信股份有限公司 | A kind of personalized position based on Similarity Measure recommends method and system |
-
2019
- 2019-12-19 CN CN201911319548.1A patent/CN111192161A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095256A (en) * | 2014-05-07 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Information push method and apparatus based on similarity degree between users |
| CN106933821A (en) * | 2015-12-29 | 2017-07-07 | 中国电信股份有限公司 | A kind of personalized position based on Similarity Measure recommends method and system |
Non-Patent Citations (2)
| Title |
|---|
| 严宇等: "基于模糊综合评价的交易结算偏差电量处理方法", 《电力系统自动化》 * |
| 张敏: "推荐算法及其在电力营销中的应用", 《中国优秀硕士学位论文全文数据库（电子期刊）工程科技Ⅱ辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111858686A (en) * | 2020-07-08 | 2020-10-30 | 深圳市富途网络科技有限公司 | Data display method and device, terminal equipment and storage medium |
| US11978116B2 (en) | 2020-07-08 | 2024-05-07 | Shenzhen Futu Network Technology Co., Ltd. | Data display method and apparatus, terminal device, and storage medium |
| CN111858686B (en) * | 2020-07-08 | 2024-05-28 | 深圳市富途网络科技有限公司 | Data display method, device, terminal equipment and storage medium |
| CN115601195A (en) * | 2022-10-17 | 2023-01-13 | 桂林电子科技大学（Cn） | Transaction bidirectional recommendation system and method based on real-time label of power user |
| CN115601195B (en) * | 2022-10-17 | 2023-09-08 | 桂林电子科技大学 | Transaction bidirectional recommendation system and method based on real-time label of power user |
| CN116707019A (en) * | 2023-05-12 | 2023-09-05 | 云南电网有限责任公司信息中心 | Electric quantity distribution method, system and computer equipment for daily electric power market |
| CN116707019B (en) * | 2023-05-12 | 2024-01-26 | 云南电网有限责任公司信息中心 | Electric quantity distribution method, system and computer equipment for daily electric power market |
| CN117273870A (en) * | 2023-11-22 | 2023-12-22 | 北京清众神州大数据有限公司 | Auxiliary decision-making method, device, equipment and storage medium for electric power market transaction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ren et al. | Demand forecasting in retail operations for fashionable products: methods, practices, and real case study | |
| Izadikhah et al. | Ranking sustainable suppliers by context-dependent data envelopment analysis | |
| Relich et al. | A fuzzy weighted average approach for selecting portfolio of new product development projects | |
| Sarkar et al. | Evaluation of supplier capability and performance: A method for supply base reduction | |
| CN111192161A (en) | Electric power market trading object recommendation method and device | |
| Mustafid et al. | Supply chain agility information systems with key factors for fashion industry competitiveness | |
| US20180308152A1 (en) | Data Processing Method and Apparatus | |
| US20100030799A1 (en) | Method for Generating a Computer-Processed Financial Tradable Index | |
| Yang et al. | SMAA-PO: project portfolio optimization problems based on stochastic multicriteria acceptability analysis | |
| Yu et al. | A multi-agent architecture for multi-product supplier selection in consideration of the synergy between products | |
| Zhang et al. | Learning to select supplier portfolios for service supply chain | |
| Silva et al. | Generation of realistic scenarios for multi-agent simulation of electricity markets | |
| CN107609771A (en) | A kind of supplier's value assessment method | |
| Stiakakis et al. | Combining the priority rankings of DEA and AHP methodologies: a case study on an ICT industry | |
| CN113642923A (en) | Bad asset pack value evaluation method based on historical collection urging data | |
| Xuefeng et al. | Predicting the final prices of online auction items | |
| CN109191205A (en) | A kind of price calculation method and terminal device based on prediction model | |
| CN115147144A (en) | Data processing method and electronic equipment | |
| Spray | Reorganise, replace or expand? The role of the supply-chain in first-time exporting | |
| Datta et al. | Comparative study on application of utility concept and VIKOR method for vendor selection | |
| Mohamed et al. | An information entropy weighting method combined to TOPSIS approach for ranking consulting firms | |
| Wu | A stochastic model for production loading in a global apparel manufacturing company under uncertainty | |
| Festervand et al. | The marketing of industrial real estate: application of Taguchi loss functions | |
| Farzamnia et al. | Group decision-making process for supplier selection using MULTIMOORA technique under fuzzy environment | |
| Manupati et al. | An integrated fuzzy MCDM approach to supplier selection—Indian automotive industry case |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200522 |
|
| RJ01 | Rejection of invention patent application after publication |