Power resource processing method, device and storage medium based on artificial intelligence

Abstract

This invention relates to an artificial intelligence-based method, apparatus, and storage medium for processing power resources, belonging to the technical field of data processing. The method includes: acquiring first electricity consumption data of a first user in a first time period; inputting the first electricity consumption data into a preset artificial intelligence network model to generate and store a first feature image of the first time period; when the first user sends a request to compare the first electricity consumption of a second time period with the first electricity consumption of the first time period, obtaining a first comparison result reflecting the color difference between the first time period and the second time period based on a pre-stored second feature image of the second time period and the first feature image; and sending the first comparison result to the first user; wherein the first comparison result is used to display to the first user.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the technical field of data processing, and more specifically, to an artificial intelligence-based power resource processing method, device, and storage medium. Background Art

[0002] With the widespread use of electric power resources, electric power resources are used in schools, enterprises or office buildings. At present, in order to be able to convert the power data used by users into more intuitive bar charts or pie charts, the existing technology can usually obtain the daily power consumption of a time period selected by the user and generate a corresponding bar chart. When the user compares the power consumption of two years horizontally, the difference in power consumption of the two months or days of the two years and the power consumption of one month or one year can be directly fed back to the user, which makes the user interface relatively cramped and the user needs to compare one by one, which is inefficient. Summary of the invention

[0003] One purpose of the embodiments of the present disclosure is to provide a new technical solution for power resource processing based on artificial intelligence.

[0004] According to a first aspect of the present invention, there is provided a method for processing electric power resources based on artificial intelligence, the method comprising:

[0005] Acquire first electricity usage data of a first user in a first time period;

[0006] Inputting the first electricity consumption data into a preset artificial intelligence network model to generate and store a first characteristic image of the first time period;

[0007] When the first user sends a first power usage comparison request for a second time period and the first time period, a first comparison result reflecting the image color difference between the first time period and the second time period is obtained according to a pre-stored second characteristic image of the second time period and the first characteristic image;

[0008] Sending the first comparison result to the first user; wherein the first comparison result is used to display to the first user; the artificial intelligence network model includes a data extraction model and a tile output model;

[0009] The step of inputting the first electricity consumption data into a preset artificial intelligence network model to generate and store a first characteristic image for the first time period includes:

[0010] Inputting the first electricity consumption data into the data extraction model to obtain a parameter group corresponding to each unit time; wherein the parameter group includes at least one electricity consumption type, the amount of electricity consumption representing the corresponding electricity consumption type, and the allocation coefficient representing the corresponding electricity consumption type, and the sum of each unit time is equal to the first time period;

[0011] Inputting the parameter group corresponding to each unit time into the block output model to obtain the feature block corresponding to each unit time;

[0012] The feature image blocks corresponding to each unit time are fused in time sequence to obtain and store the first feature image.

[0013] Optionally, the tile output model includes a first input channel, a second input channel and a third input channel;

[0014] The step of inputting the parameter group corresponding to each unit time into the block output model to obtain the feature block corresponding to each unit time includes:

[0015] The first power consumption is input into the first input channel of the block output model, the first allocation coefficient is input into the second input channel of the block output model, and the first power consumption type is input into the third input channel of the block output model to obtain a first characteristic block; wherein the characteristic blocks corresponding to each unit time include the first characteristic block, each unit time includes a first unit time, and the parameter group corresponding to the first unit time includes the first power consumption type, the first power consumption and the first allocation coefficient.

[0016] Optionally, the first electricity consumption data includes a sharing ratio value; the electricity consumption type includes a self-funded type, a partially funded type and a publicly funded type, and different electricity consumption types correspond to different sharing coefficients;

[0017] Among them, the apportionment coefficients corresponding to the self-funded type and the publicly funded type are fixed values, and the apportionment coefficient corresponding to the partial investment type is related to the apportionment ratio value.

[0018] Optionally, before fusing the feature image blocks corresponding to each unit time in time order to obtain and store the first feature image, the method further includes:

[0019] According to the time length of the feature image block corresponding to each unit time, the fusion reference data corresponding to each unit time is obtained; wherein the fusion reference data includes the image fusion ratio and the unit time length;

[0020] The step of fusing the feature image blocks corresponding to each unit time in time order to obtain and store the first feature image includes:

[0021] According to the image fusion ratio, the feature blocks corresponding to each unit time are fused once to obtain a fused block;

[0022] The fused images of each unit time are fused twice in time sequence to obtain the first characteristic image, and the unit time length corresponding to each unit time is associated with the first characteristic image and stored.

[0023] Optionally, the method further comprises:

[0024] When the first user sends a second electricity usage comparison request for a third time period and the first time period for one of the electricity usage types, determining the electricity usage allocation amount for the first time period for the one of the electricity usage types according to the first feature image;

[0025] Obtaining a second comparison result according to the electricity consumption apportionment amount, the electricity consumption corresponding to one of the electricity consumption types in the third time period, and the apportionment coefficient;

[0026] The second comparison result is sent to the first user; wherein the second comparison result is used to be displayed to the second user.

[0027] Optionally, obtaining a first comparison result reflecting an image color difference between the first time period and the second time period according to the pre-stored second feature image and the first feature image about the second time period includes:

[0028] Comparing the fused image blocks of the first feature image and the pre-stored fused image blocks of the second feature image for the second time period one by one in time order to obtain image color difference values ​​corresponding to each unit time;

[0029] A compared image is obtained according to the image color difference corresponding to each unit time, and is used as a first comparison result reflecting the image color difference between the first time period and the second time period.

[0030] According to a second aspect of the present invention, there is also provided an artificial intelligence-based power resource processing device, the device comprising:

[0031] A data acquisition module, used to acquire first electricity consumption data of a first user in a first time period;

[0032] An image generation module, used for inputting the first electricity consumption data into a preset artificial intelligence network model to generate and store a first characteristic image of the first time period;

[0033] a result obtaining module, configured to obtain a first comparison result reflecting the first time period and the second time period according to a pre-stored second characteristic image of the second time period and the first characteristic image when the first user sends a first power consumption comparison request for the second time period and the first time period;

[0034] A result sending module is used to send the first comparison result to the first user; wherein the first comparison result is used to display to the first user; the artificial intelligence network model includes a data extraction model and a tile output model;

[0035] The image generation module is further used to input the first power consumption data into the data extraction model to obtain a parameter group corresponding to each unit time; wherein the parameter group includes at least one power consumption type, the power consumption representing the corresponding power consumption type, and the allocation coefficient representing the corresponding power consumption type, and the sum of each unit time is equal to the first time period;

[0036] Inputting the parameter group corresponding to each unit time into the block output model to obtain the feature block corresponding to each unit time;

[0037] The feature image blocks corresponding to each unit time are fused in time sequence to obtain and store the first feature image.

[0038] According to the third aspect of the present invention, there is also provided an artificial intelligence-based power resource processing device, comprising a memory and a processor, wherein the memory is used to store a computer program; the processor is used to execute the computer program to implement the method according to the first aspect of the present invention.

[0039] According to a fourth aspect of the present invention, there is further provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method according to the first aspect of the present invention is implemented.

[0040] One beneficial effect of the disclosed embodiment is that by inputting the first power consumption data into the artificial intelligence network model, the first power consumption data can be converted into a first characteristic image. When the first user compares the power consumption of the second time period with that of the first time period, the second characteristic image can be compared with the first characteristic image to obtain a first comparison result. On the premise that the power consumption of the second time period is displayed in the user interface, the first comparison result in the form of an image can better reflect the difference in power consumption of the first user in the first time period and the second time period, so as to improve the comprehensiveness of the user interface displaying the power consumption of the user. The first comparison result in the form of an image makes it easier for the user to intuitively determine that the power consumption difference between the first time period and the second time period is large, shortening the process of the user querying the day with the largest difference between the two time periods, and improving the user experience.

[0041] Other features and advantages of the embodiments of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present invention and, together with the description, serve to explain the principles of the embodiments of the present disclosure.

[0043] Figure 1 is a schematic diagram of the composition structure of an artificial intelligence-based power resource processing system to which an artificial intelligence-based power resource processing method according to an embodiment can be applied;

[0044] Figure 2 is a flow chart of an artificial intelligence-based power resource processing method according to an embodiment;

[0045] Figure 3 is a user-side interface diagram according to an embodiment;

[0046] Figure 4 is a schematic diagram of the structure of an artificial intelligence network model according to an embodiment;

[0047] Figure 5 is a block schematic diagram of an artificial intelligence-based power resource processing device according to one embodiment;

[0048] Figure 6 It is a schematic diagram of the hardware structure of an artificial intelligence-based power resource processing device according to one embodiment. DETAILED DESCRIPTION

[0049] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0050] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0051] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0052] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0053] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0054] <System Embodiment>

[0055] Figure 1 1 is a schematic diagram of the composition structure of an artificial intelligence-based power resource processing system to which an artificial intelligence-based power resource processing method according to an embodiment can be applied. Figure 1 As shown, the system includes a power resource processing device 1000, a user terminal 2000 and a sampling device 3000, and the system can be applied to a school scenario.

[0056] The above user terminal 2000 is a terminal device used by a user, and the terminal device is, for example, a mobile phone, a personal computer, a notebook or a tablet, etc., which is not limited here.

[0057] The above sampling device 3000 is set in the school teaching building, dormitory unit building and laboratory area. The sampling device 3000 can sample the power consumption generated by a room in different areas. The sampling device 3000 is an existing voltage sampling device or a current sampling device, which is not limited here. The sampling device 3000 can feed back the power consumption generated by each user in different areas to the power resource processing device 1000 based on artificial intelligence.

[0058] The above-mentioned artificial intelligence-based power resource processing device 1000 is, for example, a server, which can be communicated with each user terminal 2000 and each sampling device 3000 through a network, so that the user can view the information on the user's use of power resources through the user terminal 2000. The artificial intelligence-based power resource processing device 1000 can also obtain the information on the user's use of power resources through the sampling device 3000, and can also display the information of the electronic resources that the user has used to the user through the user terminal 2000.

[0059] As applied to the embodiments of the present disclosure, the memory of the power resource processing device 1000 based on artificial intelligence is used to store a computer program, which is used to control the processor of the power resource processing device 1000 based on artificial intelligence to operate according to the power resource processing method based on artificial intelligence in any embodiment. A technician can design a computer program according to the scheme of the embodiments of the present disclosure. How the computer program controls the processor to operate is well known in the art, so it will not be described in detail here.

[0060] <Method Example>

[0061] Figure 2 is a flowchart of an artificial intelligence-based power resource processing method according to an embodiment. Figure 1 An artificial intelligence-based power resource processing device.

[0062] like Figure 2 As shown, the power resource processing method based on artificial intelligence in this embodiment may include the following steps S210 to S240:

[0063] Step S210: Acquire first electricity usage data of a first user in a first time period.

[0064] In this embodiment, the first time period is, for example, a month or a year, which is not limited here.

[0065] In some examples, the first electricity consumption data may include the electricity consumption used by the first user in the first time period, the electricity consumption for daily use, the electricity consumption for laboratory use, the number of participants and the cost sharing, the electricity consumption for classroom use, the cost per kilowatt-hour in the first time period, etc., which are not limited here. Among them, the cost sharing can be shared by user A and user B, or by the school, user A and user B. The specific sharing method is manually set and is not limited here.

[0066] In some examples, the first power consumption data used by the first user can be obtained in different ways, such as directly obtained through data on the user terminal of the first user, or through a sampling device to feedback a usage curve of power consumption generated by a room used by the first user, which is not limited here. Among them, when the user terminal of the first user uses a room or laboratory in a certain teaching building, it is necessary to punch in the control interface of the user terminal, so that the power resource processing device based on artificial intelligence can receive the user's punch-in operation, and obtain the power consumption generated by the user using the room in the first time period through the sampling device corresponding to the room, and use the usage curve of these power consumption as the first power consumption data of the first user. The power resource processing device based on artificial intelligence can also obtain the natural loss of power consumption generated by the room through the usage curve, wherein obtaining natural loss through the usage curve is a prior art and is not specifically described here. By removing the portion corresponding to the natural consumption generated by the user using the room from the usage curve, and using the usage curve excluding the natural loss portion as the first power consumption data of the first user for the room in the first time period, the accuracy of the first power consumption data can be effectively improved.

[0067] Step S220: input the first electricity consumption data into a preset artificial intelligence network model to generate and store a first feature image of a first time period.

[0068] Step S230, when the first user sends a first power usage comparison request for the second time period and the first time period, a first comparison result reflecting the image color difference between the first time period and the second time period is obtained according to the pre-stored second feature image and the first feature image for the second time period.

[0069] In some examples, taking the first time period and the second time period both being a certain month as an example, the first time period is January and the second time period may be January of the next year.

[0070] Step S240: Send the first comparison result to the first user; wherein the first comparison result is used to display to the first user.

[0071] In some examples, such as Figure 3 As shown, the first time period is October 24, and the second time period is October 23. After comparison, the image can be rendered into different colors for the area corresponding to October 01-31 in the area of ​​total electricity consumption this month according to the image color difference corresponding to October 01-31 in 23 and 24. Rendering different colors according to the image color difference is a prior art and will not be elaborated on here. The first comparison result of user A may also include an increase of 60 degrees in total electricity consumption compared to last year.

[0072] In some embodiments, in order to realize the conversion of data into images for storage, the artificial intelligence network model may include a data extraction model and a tile output model. Step S220 may include the following steps S221 to S223:

[0073] Step S221, input the first electricity consumption data into the data extraction model to obtain a parameter group corresponding to each unit time; wherein the parameter group includes at least one electricity consumption type, the electricity consumption representing the corresponding electricity consumption type and the allocation coefficient representing the corresponding electricity consumption type, and the sum of each unit time is equal to the first time period.

[0074] In this embodiment, taking the first time period as a month as an example, each unit time is, for example, a day in the month. For example, the first time period is October, and each unit time is from October 1 to October 31.

[0075] In some examples, electricity usage types may include self-funded type, partially funded type and publicly funded type, wherein the self-funded type corresponds to the user using household electricity at his own expense, the partially funded type corresponds to the user and other users using the laboratory and needing to bear part of the cost or the user and the school using the laboratory and needing to bear part of the cost, and the publicly funded type corresponds to the school bearing all the costs, for example, the user carrying out teaching tasks in the classroom, etc.

[0076] In some examples, different electricity usage types can be represented by different identifiers. Taking the self-funded type as "a", the partially funded type as "b", and the publicly funded type as "c" as an example, the parameter group for the self-funded type of user A in the first time period can be [a, 8:00-10:00, 5:00-8:00 in the first time period, 5, 1per], where "5" represents 5 degrees of electricity consumption and "1per" represents the sharing coefficient of 1.

[0077] Step S222, input the parameter group corresponding to each unit time into the block output model to obtain the feature block corresponding to each unit time.

[0078] In this embodiment, the electricity usage type, electricity usage, and allocation coefficient in the parameter group corresponding to each unit time are respectively input into different channels in the image output model to generate a feature block corresponding to each unit time.

[0079] Step S223, the feature image blocks corresponding to each unit time are merged in time sequence to obtain and store a first feature image.

[0080] In this embodiment, taking unit time a as an example, the feature block corresponding to the self-funded type is A1, the feature block corresponding to the partially funded type is A2, and the feature block corresponding to the publicly funded type is A3. The generated feature blocks of unit time a can be spliced ​​according to the set order, and A1, A2 and A3 are sequentially spliced ​​into a fused block A0, and the fused block A0 is a part of the first feature image. Among them, the set order is, for example, self-funded type-partially funded type-publicly funded type. By fusing the feature blocks according to the set order, the storage of the order of each feature block can be effectively reduced.

[0081] In some embodiments, the tile output model includes a first input channel, a second input channel, and a third input channel. Step S222 may include the following steps S2221:

[0082] Step S2221, input the first power consumption into the first input channel of the block output model, input the first allocation coefficient into the second input channel of the block output model, and input the first power consumption type into the third input channel of the block output model to obtain the first characteristic block; wherein the characteristic blocks corresponding to each unit time include the first characteristic block, each unit time includes the first unit time, and the parameter group corresponding to the first unit time includes the first power consumption type, the first power consumption and the first allocation coefficient.

[0083] In this embodiment, the image output model is, for example, a color mapping model, the first input channel is, for example, an R channel, the second input channel is, for example, a G channel, and the third input channel is, for example, a B channel.

[0084] In this embodiment, the first electricity usage type can be any one of the self-funded type, the partially funded type and the publicly funded type, the first electricity usage is the electricity usage corresponding to the first electricity usage type, and the first apportionment coefficient is the apportionment coefficient corresponding to the first electricity usage type.

[0085] In some examples, the parameter group for the self-paid type of user A in the first time period is [a, 8:00-10:00, 5:00-8:00 in the first time period, 5, 1per], then the electricity consumption of the first electricity consumption type is 5 kWh, and the first allocation coefficient is 1.

[0086] In some examples, such as Figure 4As shown, the data extraction model is, for example, a pre-trained model, and the image output model is, for example, a color mapping model. The pre-trained model can extract each type of electricity in the electricity data and the corresponding power consumption and allocation coefficient of each type of electricity from the power consumption data in different formats and arrangements output by different sampling devices or user terminals. After normalizing the power consumption types and the corresponding power consumption and allocation coefficients extracted by the pre-trained model, normalized values ​​are obtained, and then these normalized values ​​are input into the block output model. The block output model can generate feature blocks a1-feature blocks a3 corresponding to unit time t1, and generate feature blocks b1-feature blocks b3 corresponding to unit time t2, and then merge feature blocks a1-feature blocks a3 of different power types into fused blocks a by splicing, and merge feature blocks b1-feature blocks b3 into fused blocks b by splicing, and fused blocks a and fused blocks b are spliced ​​into feature images A according to time sequence.

[0087] In some examples, the artificial intelligence network model can be trained by a large number of sample sets, and the loss values ​​obtained after the large number of sample sets are processed by the data extraction model and the tile output model are used to calibrate the artificial intelligence network model to improve the accuracy of the artificial intelligence network model.

[0088] In other words, by setting the block output model, corresponding feature blocks can be generated based on parameter groups of different electricity consumption types, thereby generating corresponding feature images, so as to realize the conversion of data into images for storage, thereby effectively improving the storage space utilization of the artificial intelligence-based power resource processing device.

[0089] In some embodiments, in order to accurately determine the electricity consumption of the partially funded type, the first electricity consumption data includes an allocation ratio value; the electricity consumption types include self-funded type, partially funded type and publicly funded type, and different electricity consumption types correspond to different allocation coefficients; among them, the allocation coefficients corresponding to the self-funded type and the publicly funded type are fixed values, and the allocation coefficient corresponding to the partially funded type is related to the allocation ratio value.

[0090] In this embodiment, the apportionment coefficient of the self-funded type is, for example, 1, and the apportionment coefficient of the public funding type is, for example, 0.01.

[0091] In some examples, the artificial intelligence-based power resource processing device pre-sets a part of the school's contribution in the partial contribution type, which is, for example, 30%, 50% or 80%. Taking the school's contribution as 30% as an example, the parameter group for the partial contribution type for user B in the first time period can be: [b, 2 o'clock-4 o'clock in the first time period, 3, 0.5per], which can indicate that user B and other users share a laboratory with a share of 50%, that is, the part borne by user B is 50%×(100%-30%)=35%. The apportionment coefficient of user B is 0.35, and the apportionment ratio value of user B is 0.5per.

[0092] In some embodiments, before step S223, the method further includes the following step S2229:

[0093] Step S2229, obtaining fusion reference data corresponding to each unit time according to the time length corresponding to the feature block corresponding to each unit time; wherein the fusion reference data includes the image fusion ratio and the unit time length.

[0094] In some examples, the feature blocks corresponding to a unit time include feature block B1 corresponding to the self-funded type, feature block B2 corresponding to the partially funded type, and feature block B3 corresponding to the publicly funded type. The time length corresponding to feature block B1 is 1 hour, the time length corresponding to feature block B2 is 0.5 hours, and the time length corresponding to feature block B3 is 1 hour. Then, the image fusion ratio is 2:1:2, and the unit time length is 0.5 hours.

[0095] Based on this, step S223 may include the following steps S2231 and S2232:

[0096] Step S2231, according to the image fusion ratio, the feature blocks corresponding to each unit time are fused once to obtain a fused block.

[0097] Step S2232: perform secondary fusion on the fused images of each unit time in chronological order to obtain a first feature image, and store the unit duration corresponding to each unit time in association with the first feature image.

[0098] Continuing with the above example, the size of the fused block is [1×1], the size of the feature block B1 is [0.4×1], the size of the feature block B2 is [0.2×1], and the size of the feature block B3 is [0.4×1], and they are spliced ​​in the order of B1-B2-B3 to obtain the fused block B0. According to the above method, different fused blocks can be obtained according to different feature blocks, and the fused blocks are spliced ​​into the first feature image in chronological order. In other words, by setting the proportion of each feature block in the fused block according to the length of time, it is convenient for users to judge the type of electricity consumption that accounts for the largest proportion of electricity resource consumption on a certain day.

[0099] In some embodiments, the method further includes the following steps S310 to S330:

[0100] Step S310, when the first user sends a second electricity usage comparison request for a third time period and a first time period for one electricity usage type, determine the electricity usage allocation amount for one electricity usage type in the first time period according to the first feature image.

[0101] In some examples, one of the electricity usage types may be any one of a self-funded type, a partially funded type, and a publicly funded type.

[0102] In some examples, the electricity consumption allocation is the electricity consumption of one of the electricity consumption types multiplied by the allocation coefficient.

[0103] In some examples, taking the first day in the first time period as an example, one of the electricity consumption types is a self-paid type, the image fusion ratio in the fusion reference data is B1: B2: B3 = 2: 1: 2, and the unit duration in the fusion reference data is 0.5 hours. According to B1: B2: B3 = 2: 1: 2 and 0.5 hours, it can be determined that the self-paid type is 1 hour. According to the first feature image, the self-paid type electricity consumption on the first day × the self-paid type allocation coefficient, that is, the self-paid type electricity allocation amount, can be determined.

[0104] Step S320, obtaining a second comparison result according to the electricity sharing amount, the electricity consumption corresponding to one of the electricity consumption types in the third time period, and the sharing coefficient.

[0105] In some examples, taking the first day in the first time period and the first day of the third time period as examples, where one of the electricity usage types is a self-paid type, the second comparison result may include the electricity usage share of the self-paid type on the first day of the first time period - the electricity usage share of the self-paid type on the first day of the third time period (the electricity usage corresponding to the self-paid type on the first day of the third time period × the sharing coefficient).

[0106] Step S330: Send the second comparison result to the first user; wherein the second comparison result is used to display to the second user.

[0107] In some examples, the first time period is September 24, and the third time period is September 23. The second comparison result displayed to the second user can be to display the image color difference for the self-paid type from September 1st to September 30th in 23 and 24, and render the area corresponding to September 1st to September 30th in the area of ​​the total amount of living electricity consumption in September displayed on the interface into different colors.

[0108] In some embodiments, in order to make the first comparison result more intuitive, step S230 may include the following steps S2301 and S2302:

[0109] Step S2301 : Compare the fused image blocks of the first feature image and the pre-stored fused image blocks of the second feature image for the second time period one by one in time order to obtain the image color difference corresponding to each unit time.

[0110] In some examples, the first feature image and the second feature image may be formed by splicing different fused tiles, such as Figure 4 As shown, the feature image B0 can be formed by splicing the fused image block a and the fused image block b.

[0111] In some examples, the fused image block corresponding to the second day in the first feature image can be compared with the fused image block corresponding to the second day in the second feature image to obtain the image color difference of the second day, that is, the image color difference.

[0112] Step S2302: obtaining a compared image according to the image color difference corresponding to each unit time, and using it as a first comparison result reflecting the image color difference between the first time period and the second time period.

[0113] In some examples, such as Figure 3 As shown, the first time period is October 24, and the second time period is October 23. After comparison, the image can be rendered into different colors for the area corresponding to October 01-31 in the area of ​​total electricity consumption this month according to the image color difference corresponding to October 01-31 in 23 and 24. Rendering different colors according to the image color difference is a prior art and will not be elaborated on here. Among them, different colors are distinguished by the number and direction of the oblique lines. For example, the area where the self-funded type on the 01st is located corresponds to a downward slanting oblique line, the area where the partially funded type on the 01st is located corresponds to three downward slanting oblique lines, and the area where the publicly funded type on the 01st is located corresponds to a blank.

[0114] <Equipment Example 1>

[0115] Figure 5 FIG. 1 is a block diagram of a power resource processing device based on artificial intelligence according to an embodiment. Figure 5 As shown, the artificial intelligence-based power resource processing device 400 may include:

[0116] The data acquisition module 410 is used to acquire first electricity consumption data of a first user in a first time period;

[0117] An image generation module 420, configured to input the first power consumption data into a preset artificial intelligence network model, and generate and store a first characteristic image of a first time period;

[0118] The result obtaining module 430 is used to obtain a first comparison result reflecting the image color difference between the first time period and the second time period according to the pre-stored second characteristic image and the first characteristic image about the second time period when the first user sends a first power consumption comparison request for the second time period and the first time period;

[0119] The result sending module 440 is used to send the first comparison result to the first user; wherein the first comparison result is used to be displayed to the first user.

[0120] Optionally, the image generation module 420 is also used to input the first electricity consumption data into the data extraction model to obtain a parameter group corresponding to each unit time; wherein the parameter group includes at least one electricity consumption type, the electricity consumption representing the corresponding electricity consumption type and the allocation coefficient representing the corresponding electricity consumption type, and the sum of each unit time is equal to the first time period; the parameter group corresponding to each unit time is input into the block output model to obtain a feature block corresponding to each unit time; the feature blocks corresponding to each unit time are fused in chronological order to obtain and store the first feature image.

[0121] Optionally, the image generation module 420 is also used to input the first power consumption into the first input channel of the block output model, input the first allocation coefficient into the second input channel of the block output model, and input the first power consumption type into the third input channel of the block output model to obtain a first feature block; wherein the feature blocks corresponding to each unit time include the first feature block, each unit time includes the first unit time, and the parameter group corresponding to the first unit time includes the first power consumption type, the first power consumption and the first allocation coefficient.

[0122] Optionally, the artificial intelligence-based power resource processing device 400 further includes a data obtaining module, which is used to obtain fusion reference data corresponding to each unit time according to the time length of the feature block corresponding to each unit time; wherein the fusion reference data includes an image fusion ratio and a unit time length;

[0123] The image generation module 420 is also used to fuse the feature blocks corresponding to each unit time once according to the image fusion ratio to obtain a fused block; fuse the fused images of each unit time twice in chronological order to obtain a first feature image, and store the unit duration corresponding to each unit time in association with the first feature image.

[0124] Optionally, the artificial intelligence-based power resource processing device 400 also includes a result display module, which is used to determine the electricity share for one of the electricity usage types in the first time period according to the first feature image when the first user sends a second electricity usage comparison request for the third time period and the first time period for one of the electricity usage types; obtain a second comparison result according to the electricity share, the electricity consumption corresponding to one of the electricity usage types in the third time period, and the sharing coefficient; send the second comparison result to the first user; wherein the second comparison result is used to display to the second user.

[0125] Optionally, the result acquisition module 430 is also used to compare the fused blocks of the first feature image and the pre-stored fused blocks of the second feature image for the second time period one by one in chronological order to obtain the image color difference corresponding to each unit time; based on the image color difference corresponding to each unit time, a compared image is obtained, and it serves as a first comparison result reflecting the image color difference between the first time period and the second time period.

[0126] The power resource processing device 400 may be Figure 1 The power resource processing device 1000 in.

[0127] <Equipment Example 2>

[0128] Figure 6 It is a schematic diagram of the hardware structure of an artificial intelligence-based power resource processing device according to another embodiment.

[0129] like Figure 6 As shown, the artificial intelligence-based power resource processing device 500 includes a processor 510 and a memory 520, wherein the memory 520 is used to store an executable computer program, and the processor 510 is used to execute a method such as any of the above method embodiments according to the control of the computer program.

[0130] The artificial intelligence-based power resource processing device 500 may be an artificial intelligence-based power resource processing device 1000 .

[0131] Each module of the above-mentioned artificial intelligence-based power resource processing device 400 can be implemented by the processor 510 in this embodiment executing a computer program stored in the memory 520, or can be implemented by other structures, which is not limited here.

[0132] The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0133] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the above. The computer-readable storage medium used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0134] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0135] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In some embodiments, the electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be executed by using the state information of the computer-readable program instructions to personalize and customize the electronic circuit, thereby implementing various aspects of the present invention.

[0136] Various aspects of the present invention are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each box of the flowchart and / or block diagram and the combination of the boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0137] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0138] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0139] The flowchart and block diagram in the accompanying drawings show the possible architecture, functions and operations of the system, method and computer program product according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of an instruction, and a part of a module, a program segment or an instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0140] Embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the marketplace, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present invention is defined by the appended claims.

Claims

1. A method for processing electric power resources based on artificial intelligence, characterized in that: The method comprises: Acquire first electricity usage data of a first user in a first time period; Inputting the first electricity consumption data into a preset artificial intelligence network model to generate and store a first characteristic image of the first time period; When the first user sends a first power usage comparison request for a second time period and the first time period, a first comparison result reflecting the image color difference between the first time period and the second time period is obtained according to a pre-stored second characteristic image of the second time period and the first characteristic image; Sending the first comparison result to the first user; wherein the first comparison result is used to display to the first user; the artificial intelligence network model includes a data extraction model and a tile output model; The step of inputting the first electricity consumption data into a preset artificial intelligence network model to generate and store a first characteristic image for the first time period includes: Inputting the first electricity consumption data into the data extraction model to obtain a parameter group corresponding to each unit time; wherein the parameter group includes at least one electricity consumption type, the amount of electricity consumption representing the corresponding electricity consumption type, and the allocation coefficient representing the corresponding electricity consumption type, and the sum of each unit time is equal to the first time period; Inputting the parameter group corresponding to each unit time into the block output model to obtain the feature block corresponding to each unit time; The feature blocks corresponding to each unit time are merged in time order to obtain and store the first feature image; the block output model includes a first input channel, a second input channel and a third input channel; the first input channel is an R channel, the second input channel is a G channel, and the third input channel is a B channel; The step of inputting the parameter group corresponding to each unit time into the block output model to obtain the feature block corresponding to each unit time includes: The first power consumption is input into the first input channel of the block output model, the first allocation coefficient is input into the second input channel of the block output model, and the first power consumption type is input into the third input channel of the block output model to obtain a first characteristic block; wherein the characteristic blocks corresponding to each unit time include the first characteristic block, each unit time includes a first unit time, and the parameter group corresponding to the first unit time includes the first power consumption type, the first power consumption and the first allocation coefficient.

2. The method according to claim 1, characterized in that The first electricity consumption data includes a sharing ratio value; the electricity consumption type includes a self-funded type, a partially funded type, and a publicly funded type, and different electricity consumption types correspond to different sharing coefficients; Among them, the apportionment coefficients corresponding to the self-funded type and the publicly funded type are fixed values, and the apportionment coefficient corresponding to the partial investment type is related to the apportionment ratio value.

3. The method according to claim 2, characterized in that Before fusing the feature image blocks corresponding to each unit time in time order to obtain and store the first feature image, the method further includes: According to the time length of the feature image block corresponding to each unit time, the fusion reference data corresponding to each unit time is obtained; wherein the fusion reference data includes the image fusion ratio and the unit time length; The step of fusing the feature image blocks corresponding to each unit time in time order to obtain and store the first feature image includes: According to the image fusion ratio, the feature blocks corresponding to each unit time are fused once to obtain a fused block; The fused images of each unit time are fused twice in time sequence to obtain the first characteristic image, and the unit time length corresponding to each unit time is associated with the first characteristic image and stored.

4. The method according to claim 3, characterized in that The method further comprises: When the first user sends a second power usage comparison request for a third time period and the first time period for one of the power usage types, determining, according to the first feature image, a power usage allocation amount for the first time period for the one of the power usage types, the power usage allocation amount being power usage of the one of the power usage types multiplied by an allocation coefficient; Obtaining a second comparison result according to the electricity consumption apportionment amount, the electricity consumption corresponding to one of the electricity consumption types in the third time period, and the apportionment coefficient; The second comparison result is sent to the first user; wherein the second comparison result is used to be displayed to the second user.

5. The method according to claim 3, characterized in that: The obtaining, based on the pre-stored second characteristic image and the first characteristic image about the second time period, a first comparison result reflecting the image color difference between the first time period and the second time period includes: Comparing the fused image blocks of the first feature image and the pre-stored fused image blocks of the second feature image for the second time period one by one in time order to obtain image color difference values ​​corresponding to each unit time; A compared image is obtained according to the image color difference corresponding to each unit time, and is used as a first comparison result reflecting the image color difference between the first time period and the second time period.

6. An artificial intelligence-based power resource processing device, characterized in that: The device comprises: A data acquisition module, used to acquire first electricity consumption data of a first user in a first time period; An image generation module, used for inputting the first electricity consumption data into a preset artificial intelligence network model to generate and store a first characteristic image of the first time period; a result obtaining module, configured to obtain, when the first user sends a first power usage comparison request for a second time period and the first time period, a first comparison result reflecting a color difference of an image between the first time period and the second time period according to a pre-stored second characteristic image of the second time period and the first characteristic image; A result sending module is used to send the first comparison result to the first user; wherein the first comparison result is used to display to the first user; the artificial intelligence network model includes a data extraction model and a tile output model; The image generation module is further used to input the first power consumption data into the data extraction model to obtain a parameter group corresponding to each unit time; wherein the parameter group includes at least one power consumption type, the power consumption representing the corresponding power consumption type and the allocation coefficient representing the corresponding power consumption type, and the sum of each unit time is equal to the first time period; input the parameter group corresponding to each unit time into the block output model to obtain a feature block corresponding to each unit time; fuse the feature blocks corresponding to each unit time in time sequence to obtain and store the first feature image; the block output model includes a first input channel, a second input channel and a third input channel; the first input channel is an R channel, the second input channel is a G channel, and the third input channel is a B channel; The image generation module is also used to input the first power consumption into the first input channel of the block output model, input the first allocation coefficient into the second input channel of the block output model, and input the first power consumption type into the third input channel of the block output model to obtain a first feature block; wherein the feature blocks corresponding to each unit time include the first feature block, each unit time includes the first unit time, and the parameter group corresponding to the first unit time includes the first power consumption type, the first power consumption and the first allocation coefficient.

7. An artificial intelligence-based power resource processing device, characterized in that: The invention comprises a memory and a processor, wherein the memory is used to store a computer program; and the processor is used to execute the computer program to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which implements the method according to any one of claims 1 to 5 when executed by a processor.

Images