CN112488800B

CN112488800B - Petroleum operation data processing method, device and storage medium based on network

Info

Publication number: CN112488800B
Application number: CN202011476089.0A
Authority: CN
Inventors: 佟力; 鲁冰; 杜彪; 裴修尧; 朱云鹏; 钟子豪
Original assignee: Beijing Yixingyuan Petrochemical Technology Co ltd
Current assignee: Beijing Yixingyuan Petrochemical Technology Co ltd
Priority date: 2020-12-15
Filing date: 2020-12-15
Publication date: 2024-01-23
Anticipated expiration: 2040-12-15
Also published as: CN112488800A

Abstract

The embodiment of the invention discloses a method, a device and a storage medium for processing petroleum operation data based on a network, wherein the method comprises the following steps: receiving petroleum operation data information sent by a client through the Internet or a virtual private network, wherein the client is a user end and/or a gas station end; safety inspection is carried out on the petroleum operation data, if the petroleum operation data contains dangerous information, the petroleum operation data is intercepted, otherwise, the petroleum operation data is released; transmitting the released petroleum operation data to a processing server for processing through the NAT gateway and the router; and programming the data processed by the processing server by utilizing a structured query language and storing the data in a database server. Thus, the safety of the petroleum operation data can be ensured, and the processing speed of the petroleum operation data can be accelerated.

Description

Petroleum operation data processing method, device and storage medium based on network

Technical Field

The invention belongs to the technical field of data processing, and particularly relates to a method and a device for processing petroleum operation data based on a network and a storage medium.

Background

With the development of society, some of the map corresponds to the service of adding a gas station, and some of the service for the gas station is developed.

However, in the operation process of the gas station, some interactive operation data of the user side or the gas station side cannot be well processed and stored.

Disclosure of Invention

In view of the above problems, the present invention provides a method, an apparatus, and a storage medium for processing petroleum operation data based on a network, so as to solve the technical problem that in the prior art, interactive operation data of some user terminals or gas station terminals cannot be well processed and stored in the operation process of a fueling station.

According to a first aspect of the present invention, there is provided a network-based petroleum operation data processing method, comprising the steps of:

receiving petroleum operation data information sent by a client through the Internet or a virtual private network, wherein the client is a user end and/or a gas station end;

carrying out safety inspection on the petroleum operation data, intercepting the petroleum operation data if dangerous information is contained in the petroleum operation data, and otherwise, releasing the petroleum operation data;

transmitting the released petroleum operation data to a processing server for processing through the NAT gateway and the router;

And programming the data processed by the processing server by utilizing a structured query language and storing the data in a database server.

Further, if the petroleum operation data is the published petroleum information sent from the gas station, the step of transmitting the released petroleum operation data to the processing server for processing through the NAT gateway and the router specifically includes:

transmitting the released release oil product information to the processing server through the NAT gateway and the router;

the processing server inputs the released oil product information into an oil product category identification model for processing, and outputs the released oil product category corresponding to the released oil product information, wherein the oil product category identification model is obtained by training a neural network by utilizing sample oil product information of a pre-marked oil product category;

the processing server searches corresponding target auditing standards in a memory according to the issued oil categories, wherein auditing standards corresponding to the oil categories are stored in the memory in advance;

the processing server checks all parameters of the released oil product information according to the target auditing standard, and if the checking is successful, the released oil product information is used as processed data;

Then, after the data processed by the processing server is programmed by using the structured query language and stored in the database server, the method further comprises:

and pushing the programmed data stored in the database server to an account platform corresponding to the gas station end for release.

Further, before the processing server inputs the released oil product information into the oil product category identification model for processing, and outputs the released oil product category corresponding to the released oil product information, the method specifically includes:

acquiring a preset number of sample oil information, and adding a corresponding oil category label for each sample oil information, wherein each sample oil information comprises a plurality of oil information data;

pre-constructing an oil product identification initial neural network with an oil product identification input layer, N oil product identification hidden layers and an oil product identification output layer, wherein the construction number N of the oil product identification hidden layers is greater than or equal to the maximum number X of oil product information data in the sample oil product information;

inputting the sample oil information from an oil identification input layer, and processing the sample oil information through the N oil identification hidden layers, wherein the first oil identification hidden layer receives data content output from the oil identification input layer, and the data of the rest oil identification hidden layers are data content output after the last oil identification hidden layer is processed;

The last oil product identification hidden layer outputs the processing result data to the oil product identification output layer so that the oil product identification output layer can determine the corresponding output oil product type according to the processing result data;

judging whether the output oil product type is the same as the corresponding oil product type label, if so, training next sample oil product information, and if not, adjusting parameters of each oil product identification hidden layer to enable the output oil product type to be the same as the corresponding oil product type label;

and taking the oil product identification initial neural network after the sample oil product information is completely trained as an oil product identification model, and storing the oil product identification model into a processing server.

Further, if the petroleum operation data is information to be distributed of petroleum knowledge sent from a gas station end and/or a user end, the step of transmitting the released petroleum operation data to a processing server for processing through a NAT gateway and a router specifically includes:

transmitting the released information to be released of the petroleum knowledge to the processing server through the NAT gateway and the router;

the processing server inputs the information to be issued of the petroleum knowledge into a knowledge category identification model for processing, and outputs a knowledge category to be issued corresponding to the information to be issued of the petroleum knowledge, wherein the knowledge category identification model is obtained by training a neural network by utilizing sample petroleum knowledge information of a pre-marked knowledge category;

The processing server marks the information to be distributed of the petroleum knowledge by utilizing the knowledge category to be distributed, and takes the marked information to be distributed of the petroleum knowledge as processed data;

and pushing the programmed data stored in the database server to the gas station end and/or an account platform corresponding to the user end for release.

Further, before the processing server inputs the information to be issued of the petroleum knowledge into a knowledge category identification model for processing and outputs a knowledge category to be issued corresponding to the information to be issued of the petroleum knowledge, the processing server specifically includes:

acquiring a preset number of sample petroleum knowledge information, and adding a corresponding knowledge category label for each sample petroleum knowledge information;

a knowledge identification initial neural network with a knowledge identification input layer, M knowledge identification hidden layers and a knowledge identification output layer is constructed in advance, wherein each knowledge identification hidden layer corresponds to and identifies the coincidence probability of one knowledge category, and the construction quantity M of the knowledge identification hidden layers is more than or equal to the category quantity maximum value Q of the knowledge category in the sample petroleum knowledge information;

Inputting the sample petroleum knowledge information from a knowledge identification input layer, and extracting keywords from the sample petroleum knowledge information by the knowledge identification input layer;

the knowledge identification input layer inputs the extracted keywords into each knowledge identification hidden layer for processing, and each knowledge identification hidden layer correspondingly outputs probability P belonging to the corresponding knowledge category ₁ ，P ₂ ，……，P _M And respectively sending the knowledge identification output layers;

the knowledge identification output layer screens out the knowledge category corresponding to the maximum value of the probability of the knowledge category as an output knowledge category, judges whether the output knowledge category is the same as the corresponding knowledge category label, if so, trains the petroleum knowledge information of the next sample, otherwise, adjusts the parameters of the knowledge identification hidden layer corresponding to the knowledge category label so that the probability of the knowledge category output after processing is 100%, and trains the petroleum knowledge information of the next sample;

and taking the knowledge identification initial neural network after the complete training of the sample petroleum knowledge information as a knowledge category identification model, and storing the knowledge category identification model into a processing server.

Further, if the oil operation data information is order data of successful transaction at the gas station end in a set time period, the step of transmitting the released oil operation data to a processing server for processing through a NAT gateway and a router specifically includes:

Transmitting order data of successful released transaction to the processing server through the NAT gateway and the router;

the processing server calculates the cost and the sum of the order data of each successful transaction according to the petroleum type and the petroleum amount in the order data of the successful transaction; calculating corresponding profit according to the cost amount and the transaction amount of the order data of each successful transaction, and establishing a coordinate system by taking the profit amount as a vertical axis and the corresponding time as a horizontal axis;

the processing server analyzes the coordinate system, determines a corresponding operation state, and takes the operation state as processed data, specifically: if the coordinate system is the overall ascending trend, determining that the account corresponding to the gas station end belongs to ascending type operation, if the coordinate system is the up-down fluctuation trend, determining that the account corresponding to the gas station end belongs to stable type operation, and if the coordinate system is the overall descending trend, determining that the account corresponding to the gas station end belongs to descending type operation;

And pushing the programmed data stored in the database server to a gas station end for display.

Further, if the petroleum operation data is an oil product inspection instruction sent from the user side and/or the gas station side, the step of transmitting the released petroleum operation data to the processing server for processing through the NAT gateway and the router specifically includes:

transmitting the released oil product inspection instruction to the processing server through the NAT gateway and the router, wherein the oil product inspection instruction contains petroleum types;

the processing server extracts the petroleum type in the petroleum product inspection instruction, and searches at least one inspection station to be determined with the petroleum type inspection qualification from a map;

the processing server acquires the position information of the user side and/or the gas station side, and searches for a determination inspection station which belongs to the same city level with the position information from at least one inspection station to be determined; if a plurality of the found definite inspection stations are arranged according to the distance from the position information from the far to the far, the distance is sent to the user side and/or the gas station side so that the user side and/or the gas station side can select a target inspection station from the plurality of definite inspection stations;

The processing server receives a released target inspection station and a released delivery time sent by the user side and/or the gas station side through the Internet or a virtual private network, acquires whether delivery service corresponding to the petroleum type of the target inspection station in the delivery time is saturated or not, generates a refusing delivery instruction to send to the user side and/or the gas station side if the delivery service is saturated, so that the user side and/or the gas station side can redetermine the target inspection station, packages the oil product inspection instruction and the delivery time if the delivery service is not saturated, and takes the packaged data as processed data;

and sending the programmed data stored in the database server to the target inspection station.

According to a second aspect of the present invention, there is provided a network-based petroleum operation data processing apparatus comprising:

the system comprises a receiving module, a processing module and a processing module, wherein the receiving module is used for receiving petroleum operation data information sent by a client through the Internet or a virtual private network, and the client is a user end and/or a gas station end;

The checking module is used for carrying out safety check on the petroleum operation data, intercepting the petroleum operation data if the petroleum operation data contains dangerous information, and otherwise, releasing the petroleum operation data;

the processing module is used for transmitting the released petroleum operation data to the processing server for processing through the NAT gateway and the router;

and the storage module is used for programming the data processed by the processing server by utilizing the structured query language and storing the data in the database server.

According to a third aspect of the present invention, there is provided an electronic device comprising a memory storing a computer program and a processor implementing the steps of the network-based oil operation data processing method of the first aspect when the computer program is executed.

According to a fourth aspect of the present invention, there is provided a storage medium having stored thereon a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the network-based oil operation data processing method of the first aspect.

The method, the device and the storage medium for processing the petroleum operation data based on the network provided by the embodiment of the invention have the following beneficial effects:

According to the technical scheme of the invention, the petroleum operation data sent by the user side and/or the gas station side through the Internet or the virtual private network is subjected to security check, after no dangerous information is determined, the petroleum operation data is transmitted to the processing server through the NAT gateway and the router to be further processed according to the specific content of the petroleum operation data, and the processing result is programmed by utilizing the structured query language and stored in the database server. Thus, the safety of the petroleum operation data can be ensured, and the processing speed of the petroleum operation data can be accelerated.

Drawings

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

The invention may be more clearly understood from the following detailed description taken in conjunction with the accompanying drawings, in which:

FIG. 1 is a flow chart of a network-based petroleum operation data processing method according to an embodiment of the present invention;

FIG. 2 is a block diagram of a petroleum data processing device based on a gas station end according to an embodiment of the present invention;

fig. 3 is a block diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

Meanwhile, it should be understood that the sizes of the respective parts shown in the drawings are not drawn in actual scale for convenience of description.

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

Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.

It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.

As shown in fig. 1, this embodiment proposes a network-based petroleum operation data processing method, which is applicable to a server, where the server belongs to a service platform that is set up in advance and that performs centralized processing on data about fueling sent from a user end and/or a fueling station end, and the user end and the fueling station end want to perform petroleum operation data processing by using the service platform, and need to install corresponding APPs or corresponding applets in advance in the user end and the fueling station end or in instant messaging. The server is a generic term for the following various servers.

The method comprises the following steps:

step 101, receiving petroleum operation data information sent by a client through the internet or a virtual private network, wherein the client is a user end and/or a gas station end.

Wherein, the virtual private network (VPN, virtual Private Network) can establish a private network on a public network for encrypted communication.

The corresponding petroleum run data may be some message data, or instruction data, or volume load data, etc.

And 102, carrying out safety inspection on the petroleum operation data, intercepting the petroleum operation data if the petroleum operation data contains dangerous information, and otherwise, releasing the petroleum operation data.

The petroleum operation data are input into the safe operation server. Statistical analysis software (SAS, statistical analysis system) is firstly utilized to carry out statistical analysis on the petroleum operation data, if the analysis is unqualified, the petroleum operation data is directly intercepted, and the transmission of the petroleum operation data is forbidden. And if the analysis is qualified, performing abnormality detection processing by using an abnormality detection protocol. If abnormality is detected, the petroleum operation data is directly intercepted, the transmission of the petroleum operation data is forbidden, and if abnormality is not detected, the petroleum operation data is released.

And step 103, transmitting the released petroleum operation data to a processing server for processing through the NAT gateway and the router.

The method comprises the steps of inputting the released petroleum operation data to a NAT (Network Address Translation ) gateway for network address translation, and transmitting the released petroleum operation data to a processing server through a router after the released petroleum operation data is translated into a website capable of entering the processing server.

And 104, programming the data processed by the processing server by using a structured query language and storing the data in a database server.

The structured query language (SQL, structured Query Language), a database query and programming language, is used for accessing data and querying, updating and managing a relational database system, and is used for programming the processed data and editing the processed data into the structured query language which can be identified by the processing server, so that the processing rate of the processing server can be increased.

According to the scheme, the petroleum operation data sent by the user side and/or the gas station side through the Internet or the virtual private network is subjected to security check, after no dangerous information is determined, the petroleum operation data is transmitted to the processing server through the NAT gateway and the router to be further processed according to the specific content of the petroleum operation data, and the processing result is programmed by utilizing the structured query language and stored in the database server. Thus, the safety of the petroleum operation data can be ensured, and the processing speed of the petroleum operation data can be accelerated.

In a specific embodiment, if the petroleum operation data is the published petroleum information sent from the gas station, step 103 specifically includes:

and step A1, transmitting the released release oil product information to a processing server through the NAT gateway and the router.

Wherein, the release of the oil information includes at least one of: oil names, oil composition components, oil unit price, oil total amount, oil production place and oil processing manufacturer.

And the user of the gas station inputs corresponding oil product release information through the gas station end so as to be checked in the later period, and release is carried out by utilizing a network after the check passes.

In addition, before the oil product information sent by the gas station end is received, a corresponding APP is installed at the gas station end in advance or a corresponding applet is loaded in instant messaging, a gas station account is established in advance, a corresponding user role is selected, and a personal user or a gas station user can be selected.

After selecting the gas station user, the interface for account registration is also popped up. Inputting the name and the password of the fueling station, packaging and sending the name and the password of the fueling station and the selected fueling station roles to a server, matching the corresponding fueling station interface according to the fueling station roles by the server, and establishing a corresponding storage database for the corresponding fueling station account number so as to store the data information of the fueling station account number. The data of each gas station user in the server is correspondingly stored in a gas station user memory, and the gas station user memory comprises a storage database corresponding to each gas station account.

Therefore, when the gas station personnel logs in again through the gas station end, an account login instruction is sent to the server, wherein the account login instruction comprises role authority information, account name, password and some basic information corresponding to the gas station end.

And after receiving the account login instruction, the server invokes relevant display information in a storage database of the corresponding gas station account from a memory of the gas station user if the role authority information is the gas station user. And sending the corresponding display information to the corresponding gas station end for display.

And step A2, the processing server inputs the released oil product information into an oil product category identification model for processing, and outputs the released oil product category corresponding to the released oil product information, wherein the oil product category identification model is obtained by training a neural network by utilizing sample oil product information of a pre-marked oil product category.

The oil category identification model is obtained by learning and training a neural network according to a plurality of groups of sample oil information of the pre-marked oil categories.

The oil product identification input layer of the oil product category identification model comprises a plurality of input ports, and each input port correspondingly inputs one item of data in the released oil product information. The number of input ports is greater than or equal to the number of items with the greatest data in the sample oil product information. The method is used for guaranteeing that each item of data in the oil product information can be input and processed simultaneously. The oil identification input layer performs data conversion processing on the released oil information and converts the released oil information into code data so that an oil identification hidden layer of an oil category identification model can process the code data, and finally released oil categories corresponding to the released oil information are obtained and output through the oil identification output layer.

And step A3, the processing server searches corresponding target auditing standards in the memory according to the issued oil categories, wherein the auditing standards corresponding to the oil categories are stored in the memory in advance.

And step A4, the processing server checks all parameters of the released oil product information according to the target audit standard, and if the checking is successful, the released oil product information is used as processed data.

Then, after step 104, further includes:

and 105A, pushing the programmed data stored in the database server to an account platform corresponding to the gas station end for release.

In the above scheme, whether the oil names in the released oil information are correct or not can be checked by utilizing the target checking standard, whether the corresponding oil composition components are within the range of each composition component corresponding to the released oil category or not, whether the unit price of the oil accords with the unit price interval corresponding to the modified released oil category released by authorities or not, whether the oil production place in the released oil information can be searched in each prestored oil production place of the released oil category or not, and the like. After all parameters in the released oil product information meet the target auditing standard, the verification can be determined to be successful, otherwise, the verification is determined to be unsuccessful, and reminding information is generated and sent to a gas station end, so that staff of the gas station can see the corresponding reminding information, and modify the released oil product information or cancel the release of the oil product.

Through the scheme, the published oil category corresponding to the published oil information can be determined according to the published oil information sent by the gas station end by utilizing the pre-built oil category identification model, so that the corresponding target auditing standard can be searched from the memory according to the published oil category, the published oil information can be audited according to the target auditing standard, and the published oil information can be published after the auditing is successful, so that the correctness of the published oil information can be improved, the later modification is avoided, and the operation is simple and quick.

In a specific embodiment, before step A2, specifically including:

step A21, obtaining a predetermined number of sample oil information, and adding a corresponding oil category label to each sample oil information, wherein each sample oil information comprises a plurality of oil information data.

And step A22, pre-constructing an oil product identification initial neural network with an oil product identification input layer, N oil product identification hidden layers and an oil product identification output layer, wherein the construction number N of the oil product identification hidden layers is more than or equal to the maximum number X of oil product information data in sample oil product information.

And step A22, inputting sample oil information from the oil identification input layer, and processing the sample oil information through N oil identification hidden layers, wherein the first oil identification hidden layer receives data content output from the oil identification input layer, and the data of the rest oil identification hidden layers are data content output after the last oil identification hidden layer is processed.

And A23, outputting the processing result data to an oil product identification output layer by the last oil product identification hidden layer so as to determine the corresponding output oil product type according to the processing result data by the oil product identification output layer.

And step A24, judging whether the output oil class is the same as the corresponding oil class label, if so, training the next sample oil information, and if not, adjusting the parameters of each oil identification hidden layer to enable the output oil class to be the same as the corresponding oil class label.

And step A25, taking the oil product identification initial neural network after the complete training of the sample oil product information as an oil product identification model, and storing the oil product identification model into a processing server.

In the above scheme, the oil product identification input layer comprises a plurality of input ports, and each input port is corresponding to one item of data in the input sample oil product information. The number of input ports is greater than or equal to the number of items with the greatest data in the sample oil product information. The method is used for ensuring that each item of data in the sample oil product information can be input and processed simultaneously. The oil identification input layer converts the sample oil information into code data so that the oil identification hidden layer can process the code data,

Each sample oil information comprises one or more of oil name, oil composition, oil unit price, oil total amount, oil production place and oil manufacturer. The number of input ports is set to the number of items with the highest data in the sample oil information. Or a number of items (for example, 5 items) higher than the maximum data in the sample oil information as the set number of input ports.

The number of the oil product identification hidden layers is consistent with the number of the input ports, each item of data in the sample oil product information is correspondingly processed by the corresponding oil product identification hidden layer, then the processing result is transmitted to the next oil product identification hidden layer for processing, the next oil product identification hidden layer combines the processing result of the last oil product identification hidden layer with the processing result of the data in one item of sample oil product information which needs to be processed by the oil product identification hidden layer, then the next oil product identification hidden layer is transmitted, and the like until the last oil product identification hidden layer transmits the final processing result to the oil product identification output layer, and the oil product identification output layer converts the processing result into corresponding character information of the output oil product category and outputs the character information.

If the output oil category is the same as the corresponding oil category label, the next sample oil information is directly processed without processing, if the output result of the oil identification initial neural network is different, the oil identification initial neural network needs to be adjusted, and parameters of each oil identification hidden layer can be manually adjusted according to experience until the output result is the same as the oil category label. Or calculating corresponding loss functions according to the output oil product types and the oil product type labels, automatically adjusting each oil product identification hidden layer according to the loss functions, and then reprocessing the sample oil product information by utilizing the adjusted oil product identification initial neural network until the output result is consistent with the oil product type labels.

After all the sample oil product information is trained, detecting the trained oil identification initial neural network by using a preset number of detection sample data, judging the accuracy of the identification result, if the accuracy exceeds a corresponding threshold value, proving that the trained oil identification initial neural network meets the standard and can be used as an oil identification neural network model, if the accuracy is smaller than the corresponding threshold value, re-selecting the sample oil product information, and re-training the oil identification initial neural network until the accuracy of the obtained oil identification initial neural network exceeds the corresponding threshold value.

And taking the final petroleum identification initial neural network as a petroleum category identification model.

Through the scheme, the petroleum category identification model obtained by training the neural network can be utilized, and when the oil category identification is carried out on the issued oil information, the accuracy of the result of the oil category identification is further improved.

In a specific embodiment, if the petroleum operation data is information to be distributed about petroleum knowledge sent from a gas station side and/or a user side, step 103 specifically includes:

and step B1, transmitting the released information to be released of the petroleum knowledge to a processing server through the NAT gateway and the router.

And step B2, the processing server inputs the information to be issued of the petroleum knowledge into a knowledge category identification model for processing, and outputs the knowledge category to be issued corresponding to the information to be issued of the petroleum knowledge, wherein the knowledge category identification model is obtained by training a neural network by utilizing sample petroleum knowledge information of a pre-marked knowledge category.

And step B3, marking the information to be distributed of the petroleum knowledge by using the knowledge category to be distributed by the processing server, and taking the marked information to be distributed of the petroleum knowledge as processed data.

Then, after step 104, further includes:

and 105B, pushing the programmed data stored in the database server to an account platform corresponding to the gas station side and/or the user side for release.

In the above scheme, the gas station user or the individual user can correspondingly issue some knowledge about the petroleum through the gas station end or the user end, such as safety knowledge during refueling, or the working principle of the vehicle engine, or the change information about the petroleum price of other countries.

The knowledge category of the information to be issued of the petroleum knowledge needs to be processed by using a knowledge category identification model, if the outputted knowledge category to be issued is different, the knowledge category label corresponding to the information mark to be issued of the petroleum knowledge can be marked, and the knowledge category identification model is trained again by using the marked information to be issued of the petroleum knowledge. And enabling the output result of the retrained knowledge category identification model to meet the requirements.

Then, after obtaining the knowledge category to be distributed, if the account platform corresponding to the gas station end and/or the user end has the knowledge category to be distributed, adding the information to be distributed of the petroleum knowledge into the knowledge category to be distributed, if not, creating a generation knowledge category, and then adding the information to be distributed of the petroleum knowledge into the knowledge category to be distributed.

Through the scheme, the petroleum knowledge information to be released can be classified by means of the knowledge category identification model, so that the petroleum knowledge information is prevented from being consulted when the number of the petroleum knowledge information is large, the consulting person can conveniently find the petroleum knowledge information, the use is convenient, and the petroleum knowledge interface can be tidier.

In a specific embodiment, before step B2, specifically including:

and step B21, acquiring a predetermined number of sample petroleum knowledge information, and adding a corresponding knowledge category label to each sample petroleum knowledge information.

Wherein the knowledge category labels include, but are not limited to, at least one of: security category, news category, usage category, basic knowledge category, etc.

And step B22, a knowledge identification initial neural network with a knowledge identification input layer, M knowledge identification hidden layers and a knowledge identification output layer is constructed in advance, wherein each knowledge identification hidden layer corresponds to the coincidence probability of identifying one knowledge category, and the construction quantity M of the knowledge identification hidden layers is more than or equal to the category quantity maximum value Q of the knowledge category in the sample petroleum knowledge information.

The knowledge identification input layer converts the sample petroleum knowledge information into code data so that the knowledge identification hidden layer can process the code data.

And step B23, inputting the sample petroleum knowledge information from a knowledge identification input layer, and extracting keywords from the sample petroleum knowledge information by the knowledge identification input layer.

The knowledge identification input layer deletes the virtual words, adjectives, punctuations and the like in the sample petroleum knowledge information, the rest characters are subjected to word division, and the divided words are used as extracted keywords.

Step B24, the knowledge identification input layer inputs the extracted keywords into each knowledge identification hidden layer for processing, and each knowledge identification hidden layer correspondingly outputs the probability P belonging to the corresponding knowledge category ₁ ，P ₂ ，……，P _M And respectively sent to the knowledge discrimination output layer.

The knowledge identification input layer inputs the extracted keywords into each knowledge identification hidden layer simultaneously for processing, each knowledge identification hidden layer carries out simultaneous processing, and the probability obtained by processing is sent to the knowledge identification output layer.

And B25, the knowledge identification output layer screens out the knowledge category corresponding to the maximum value of the probability of the knowledge category as the output knowledge category, judges whether the output knowledge category is the same as the corresponding knowledge category label, if so, trains the petroleum knowledge information of the next sample, otherwise, adjusts the parameters of the knowledge identification hidden layer corresponding to the knowledge category label so that the probability of the knowledge category output after processing is 100%, and trains the petroleum knowledge information of the next sample.

If the maximum value of the probability of screening the knowledge categories by the knowledge identification output layer is two, the two output knowledge categories are correspondingly output, and then parameters of the knowledge identification hidden layer corresponding to the knowledge category label are adjusted so that the probability of the knowledge categories output after processing is 100%, and then the petroleum knowledge information of the next sample is trained.

And step B26, taking the knowledge identification initial neural network after the complete training of the sample petroleum knowledge information as a knowledge category identification model, and storing the knowledge category identification model into a processing server.

After all the sample petroleum knowledge information is trained, detecting the trained knowledge identification initial neural network by using a preset number of detection sample data, judging the accuracy of the identification result, if the accuracy exceeds a corresponding threshold value, proving that the trained knowledge identification initial neural network accords with a standard and can be used as a knowledge category identification model, if the accuracy is smaller than the corresponding threshold value, re-selecting the information sample data, and retraining the knowledge identification initial neural network until the accuracy of the obtained knowledge identification initial neural network exceeds the corresponding threshold value.

And taking the final knowledge identification initial neural network as a knowledge category identification model.

Through the scheme, the knowledge category identified through the knowledge category identification model can be ensured to be more accurate, petroleum knowledge information is not required to be classified manually, and the use is convenient.

In a specific embodiment, if the oil operation data information is order data of successful transaction at the gas station end within a set period of time, step 103 specifically includes:

and step C1, transmitting order data of successful released transaction to a processing server through the NAT gateway and the router.

And step C2, the processing server calculates the cost amount of the order data of each successful transaction according to the petroleum type and petroleum amount in the order data of the successful transaction. And calculating corresponding profit amount according to the cost amount and the transaction amount of the order data of each transaction success, and establishing a coordinate system by taking the profit amount as a vertical axis and the corresponding time as a horizontal axis.

Step C3, the processing server analyzes the coordinate system, determines the corresponding operation state, and takes the operation state as processed data, specifically: if the coordinate system is the overall ascending trend, the account corresponding to the gas station end is determined to belong to ascending type operation, if the coordinate system is the up-and-down fluctuation trend, the account corresponding to the gas station end is determined to belong to stable type operation, and if the coordinate system is the overall descending trend, the account corresponding to the gas station end is determined to belong to descending type operation.

Then, after step 104, further includes:

and 105, pushing the programmed data stored in the database server to a gas station end for display.

Through the scheme, the corresponding coordinates can be established according to the profit situation of the historical order data of the gas station, and then the operation situation of the account corresponding to the gas station terminal is determined through the trend displayed on the coordinates. And further, the gas station is informed to carry out corresponding operation adjustment in time, and the condition of bankruptcy caused by poor operation of the gas station is reduced.

In addition, if the gas station is determined to belong to the descent type operation, some articles or strategies about the operation of the gas station can be obtained from the network and pushed to the gas station end together for viewing by a responsible person of the gas station. And further, the operation strategy of the gas station can be improved.

In an embodiment, if the petroleum operation data is an oil inspection instruction sent from the user side and/or the gas station side, step 103 specifically includes:

and D1, transmitting a released oil product inspection instruction to a processing server through the NAT gateway and the router, wherein the oil product inspection instruction contains oil types.

And D2, extracting the petroleum types in the petroleum type inspection instruction by the processing server, and searching at least one inspection station to be determined, which has petroleum type inspection qualification, from the map.

And D3, the processing server acquires the position information of the user side and/or the gas station side, and searches for a determination inspection station which belongs to the same city level with the position information from at least one inspection station to be determined. If a plurality of the found definite inspection stations are arranged according to the sequence of distance from the position information from the far end, the distance is sent to the user end and/or the gas station end, so that the user end and/or the gas station end can select a target inspection station from the plurality of definite inspection stations.

And D4, the processing server receives the released target inspection station and the released delivery time sent by the user side and/or the gas station side through the Internet or the virtual private network, acquires whether the delivery service corresponding to the petroleum type of the target inspection station in the delivery time is saturated or not, generates a refusing delivery instruction to send the refusing delivery instruction to the user side and/or the gas station side so as to allow the user side and/or the gas station side to re-determine the target inspection station, and packages the oil product inspection instruction and the delivery time if the refusing delivery instruction is not saturated, and takes the packaged data as processed data.

Then, after step 104, further includes:

step 105D, the programmed data stored in the database server is sent to the destination checkpoint.

In the above-mentioned scheme, if the client is a gas station end, the gas station may need to put some brands of oil or some quality oils on the shelf, but the brands of oil or the quality oils need to be checked and confirmed by the inspection station. However, since the inspection service corresponding to the inspection station may be busy, in order to facilitate this process, the time waste is avoided, and the gas station end may perform the search and determination through the server.

If the gas station end wants to check for a certain type of oil K, an oil check instruction is sent to the server.

The map is a geographical location map of each inspection station with petroleum inspection qualification. The corresponding oil types of inspection qualification are marked on each inspection station in the map in advance, so that corresponding searching can be carried out in the map according to the oil types in the oil inspection instruction.

For a certain filling station end, only the inspection results from the inspection stations of the places can be effective, so that the inspection stations corresponding to the municipal institutions need to be searched correspondingly as the determined inspection stations of the filling station end. The number of the found definite inspection stations can be one or more.

In addition, if the corresponding definite inspection stations cannot be found in the same city level, the range is enlarged to find the definite inspection stations in the provincial level, and if the definite inspection stations in the provincial level are not found, the definite inspection stations in the national range are found.

If the found definite check-out station is one, the definite check-out station is directly sent to the client side so that the user of the gas station can confirm at the client side. If there are a plurality of check stations, the user of the gas station needs to select according to his actual situation.

After the processing server sends the oil product inspection instruction to the target inspection station, a corresponding unique determination code is generated, and the mailing information of the target inspection station and the unique determination code are integrated and then sent to the client. Thus, the user of the gas station can mail the unique identification code on the oil sample to the target inspection station according to the corresponding mail information. After the target inspection station receives the oil sample, judging whether the corresponding unique determination code is correct, if so, detecting the oil sample, and providing a corresponding detection report. Uploading the detection report carrying the unique determination code to a processing server, determining a client of a corresponding gas station user according to the unique determination code by the processing server, and sending the detection report to the client for query display.

Through the scheme, the user of the gas station does not need to arrive at the inspection station to perform oil product inspection on site, so that the whole oil product inspection process is more convenient and faster.

In a specific embodiment, if the petroleum running data is a sub-account application instruction sent from a gas station end corresponding to a general account, the specific processing procedure of the processing server in step 103 includes:

step E1, receiving a sub-account application instruction sent by a gas station end corresponding to a total account, wherein the sub-account application instruction comprises: the terminal identification code of the gas station end corresponding to the sub-account, the application address of the sub-account and the service item of the sub-account.

And E2, auditing the sub-account application instruction, and determining whether various information in the sub-account application instruction is real or not.

And E3, if the auditing is successful, constructing a sub-database corresponding to the sub-account in the account management database of the general account so that the sub-account can store successful service item information in the sub-database, and if the auditing is failed, generating an application failure instruction and feeding back to a gas station end corresponding to the general account so that the gas station end corresponding to the general account can modify or cancel the sub-account application instruction.

In the above scheme, if the gas station wants to set up a subordinate gas station, the setting up can be performed by the above method, the total account number of the gas station can set up a plurality of sub-accounts, and the total account number can call various data of the corresponding sub-accounts by querying the sub-database.

In addition, the order data of each sub account number daily, weekly, quarterly or annually can be counted, and the counted result is sent to the general account number. And each sub-account can be further provided with a corresponding sub-account, and after the data of each sub-account are statistically summarized and sent to the sub-account, the sub-account is further summarized and sent to the general account.

Therefore, if the gas station wants to expand the operating range, the sub account number is established, and the setting can be performed through the scheme, so that diversified services are provided for the gas station user, and the gas station is convenient to expand the scale.

Based on the schemes of the above embodiments, further description will be made, and the specific schemes are as follows:

whether it is a gas station or a user, the user needs to log in a pre-established account to use the function of the present application, and uses the corresponding account login instruction as petroleum operation data, and the specific processing procedure of the processing server in step 103 includes:

and F1, receiving an account login instruction sent by the client, and authenticating the account login instruction with corresponding account information in a database.

In the step, an individual user or a gas station user wants to log in own account, corresponding account information and account passwords need to be input into an APP or an embedded applet of a client, and the client maps and associates the account information and the account passwords to form an account login instruction and sends the account login instruction to a server.

After receiving the account login instruction, the server firstly extracts account information in the account login instruction, searches a corresponding storage database according to the account information, then extracts an account password, and compares the account password with passwords stored in the storage database, wherein the comparison is successful, namely authentication is successful.

And F2, after the authentication is successful, acquiring a corresponding Token signature, and combining the Token signature with an account login instruction to generate Token data.

The Token signature and the account login instruction are integrated together to generate Token data.

And F3, generating JWT data according to the Token data, and feeding the JWT data back to the client so that the client can determine corresponding role authority information according to the JWT data.

Wherein JWT (Json web token, network data tag specification). The JWT data includes a header, a payload, and a signature, where the header is a corresponding file type, the payload is a data object (e.g., a user's petroleum order data information), etc., the signature is Token data, the Token data is consolidated as JWT data, and the JWT data is then sent to a corresponding client.

After receiving the JWT data, the APP or applet in the client extracts Token data therein and stores it in a cookie repository in the client. Wherein the cookie repository is a database stored on the user's local terminal. Generating a resource access request through GET or POST according to the JWT data. The GET or POST is two basic request commands of the http request, and any one of the two commands can be selected to generate the resource access request. The resource access request includes: personal information access, personal location information access, historical order information access, and other information access requests corresponding to information that can be presented in an APP or applet corresponding interface are all focused on the resource access request.

The resource access request of the client contains corresponding Token data. After the resource access request is generated, in order to ensure confidentiality of the resource access request, the resource access request needs to be encrypted in advance, wherein Token data is not encrypted during encryption, so that later retrieval and searching can be performed.

Then, the client extracts Token data in the resource access request to find out whether the matched Token data exists in a cookie storage library of the client, if so, the matching is proved to be successful, a configuration file stored locally in the client is directly called, signature information and an encryption key corresponding to the Token data are obtained from the configuration file, the resource access request is decoded by utilizing the encryption key, and meanwhile, the signature information and the Token data are subjected to signature verification.

After the client decodes the resource access request successfully and the signature verification is successful, the corresponding role authority information is acquired, and the role authority information is sent to the server.

And F4, receiving the role authority information sent by the client to acquire corresponding display information, and sending the display information to the corresponding client.

Thus, the server can acquire the corresponding display information according to the role authority information. For example, some display contents required by the user aimed at by the server and stored contents in the database corresponding to the personal account are combined into display information together and sent to the client.

Through the scheme, the confidentiality of account information of the user can be guaranteed, the data transmission process can be accelerated, the accuracy of data transmission is improved, and the efficiency is improved.

Another expansion scheme is as follows:

the information identification neural network model can be used for processing the owner information and/or the vehicle information of the user terminal account or the owner information and/or the vehicle information of the resident user corresponding to the gas station terminal account, determining the corresponding first petroleum type, determining corresponding target petroleum information according to the first petroleum type, and recommending the target petroleum information to each resident user corresponding to the user terminal account or the gas station terminal account.

The owner information includes: name, age, sex, personal preference, weight, etc., the vehicle information includes: vehicle model, brand, displacement, vehicle model, color, etc.

The specific training process of the information identification neural network model is as follows:

step G1, acquiring a predetermined number of information sample data, and adding a corresponding petroleum type label to each information sample data, wherein the information sample data comprises: personal sample information and/or vehicle sample information, the number of petroleum type tags is one or more.

Step G2, pre-constructing an information identification initial neural network, wherein the information identification initial neural network comprises: an information identification input layer, N information identification hidden layers and an information identification output layer.

And G3, inputting information sample data from the information identification input layer, and processing the information sample data through N information identification hidden layers, wherein the first information identification hidden layer receives data content output from the information identification input layer, and the rest information identification hidden layers are data content output after the last information identification hidden layer is processed.

And G4, outputting the processing result data to the information identification output layer by the last information identification hidden layer so that the information identification output layer can determine the corresponding petroleum type according to the processing result data.

And G5, judging whether the output petroleum type is the same as the corresponding petroleum type label, if so, training the next information sample data, and if not, adjusting parameters of each information identification hidden layer to enable the output petroleum type to be the same as the corresponding petroleum type label.

And G6, taking the information identification initial neural network after the information sample data are completely trained as an information identification neural network model.

In the above scheme, the information identification input layer comprises two types of input ports, specifically: the vehicle owner information input port and the vehicle information input port are used for inputting the vehicle owner information and/or the vehicle information in the information sample data from the corresponding input ports, and after the data processing is carried out through the information identification input layer, the text data is converted into code data so that the information identification hidden layer can carry out further information processing according to the data.

The number of the information identification hidden layers can be set according to the number of the information categories in the personal sample information or the vehicle sample information, one information identification hidden layer correspondingly processes one type of sample information, then the processing result is transmitted to the next information identification hidden layer for processing, the next information identification hidden layer combines the processing result of the last information identification hidden layer with the processing result of the sample information of the category corresponding to the information identification hidden layer, then the next information identification hidden layer is transmitted, and the like until the last information identification hidden layer transmits the final processing result to the information identification output layer, and the information identification output layer converts the processing result into corresponding character information of the petroleum type and outputs the character information.

If the output petroleum type is the same as the corresponding petroleum type label, the next information sample data is directly processed without processing, if the output result of the information identification initial neural network is different, the information identification initial neural network needs to be adjusted, and parameters of each information identification hidden layer can be manually adjusted according to experience until the output result is the same as the petroleum type label. Or calculating a corresponding loss function according to the output petroleum type and petroleum type label, automatically adjusting each information identification hidden layer according to the loss function, and then using the adjusted information identification initial neural network to reprocess the information sample data until the output result is consistent with the petroleum type label.

After all the information sample data are trained, the trained information identification initial neural network is detected by using a preset number of detection sample data, the accuracy of the identification result is judged, if the accuracy exceeds a corresponding threshold, the trained information identification initial neural network can be used as an information identification neural network model according to the standard, if the accuracy is smaller than the corresponding threshold, the information sample data are required to be selected again, and the information identification initial neural network is trained again until the accuracy of the obtained information identification initial neural network exceeds the corresponding threshold.

And taking the final information identification initial neural network as an information identification neural network model.

A further development is as follows:

extracting corresponding historical petroleum order information of successful transaction from a user side, or extracting historical petroleum order information of successful transaction of each resident user from a gas station side; if the historical petroleum order information is acquired by the gas station end, dividing the historical petroleum order information according to each resident user, wherein each resident user corresponds to a group of historical petroleum order information which is successfully placed by the resident user at the gas station.

And inputting the extracted historical petroleum order information into an order identification neural network model, processing to obtain a corresponding second petroleum type, searching corresponding target petroleum information according to the second petroleum type, and recommending the target petroleum information to a corresponding user terminal or a user terminal corresponding to a resident user.

Or combining the first petroleum type and the second petroleum type to determine corresponding target petroleum information, and recommending the target petroleum information to a corresponding user terminal or a user terminal corresponding to a resident user.

The training process of the order recognition neural network model comprises the following steps:

and step I1, acquiring a preset number of petroleum order sample data, and adding corresponding petroleum type labels for each petroleum order sample data, wherein the number of the petroleum type labels is one or more.

Step I2, pre-constructing an order identification initial neural network, wherein the order identification initial neural network comprises: order identification input layer, M order identification hidden layers, order identification output layer.

And step I3, inputting the petroleum order sample data from an order identification input layer, and processing the petroleum order sample data through M order identification hidden layers, wherein the first order identification hidden layer receives data content output from the order identification input layer, and the rest order identification hidden layers are data content output after the last order identification hidden layer is processed.

And step I4, outputting the processing result data to an order identification output layer by the last order identification hidden layer so that the order identification output layer can determine the corresponding petroleum type according to the processing result data.

And I5, judging whether the output petroleum type is the same as the corresponding petroleum type label, if so, training the next petroleum order sample data, if not, calculating an order loss function according to the output petroleum type and the corresponding petroleum type label, and adjusting parameters of an order identification hidden layer according to the order loss function to enable the output petroleum type to be the same as the corresponding petroleum type label.

And step I6, taking the order identification initial neural network after the complete training of the petroleum order sample data as an order identification neural network model.

In the above scheme, the system comprises a plurality of input ports, and each input port can input order data. The number of input ports is equal to or greater than the maximum order data number. To ensure that multiple order data can be entered simultaneously. The order identification input layer performs data conversion processing on the order sample data and converts the order sample data into code data so that the order identification hidden layer can be processed according to the code data.

The order sample data comprises a plurality of order data groups, each order data group is the order data of the same user, each order data group can contain one or more order data, and the number of input ports takes the maximum order number in the order data group as the set number of the input ports. Or a predetermined value (e.g., 5) higher than the maximum order number as the set number of the input ports, so that the number of the input ports can be ensured to meet the demand in practical cases.

The number of the order identification hidden layers is consistent with the number of the input ports, each order is corresponding to one order data by the hidden layer, then the processing result is transmitted to the next order identification hidden layer for processing, the next order identification hidden layer combines the processing result of the last order identification hidden layer with the processing result of the order data corresponding to the order identification hidden layer, then the next order identification hidden layer is transmitted, and the like until the last order identification hidden layer transmits the final processing result to the order identification output layer, and the order identification output layer converts the processing result into corresponding character information of the petroleum type and outputs the character information.

If the output petroleum type is the same as the corresponding petroleum type label, the next information sample data is directly processed without processing, if the output result of the order identification initial neural network is different, the order identification initial neural network needs to be adjusted, and parameters of all order identification hidden layers can be manually adjusted according to experience until the output result is the same as the petroleum type label. Or calculating a corresponding loss function according to the output petroleum type and petroleum type label, automatically adjusting each order identification hidden layer according to the loss function, and then reprocessing the order sample data by using the adjusted order identification initial neural network until the output result is consistent with the petroleum type label.

After all the order sample data are trained, the trained order identification initial neural network is detected by using a preset number of detection sample data, the accuracy of the identification result is judged, if the accuracy exceeds a corresponding threshold, the trained order identification initial neural network is proved to be in conformity with the standard and can be used as an order identification neural network model, if the accuracy is smaller than the corresponding threshold, the information sample data are required to be selected again, and the order identification initial neural network is trained again until the accuracy of the obtained order identification initial neural network exceeds the corresponding threshold.

And taking the final order recognition initial neural network as an order recognition neural network model.

In a specific extension scheme, if the petroleum operation data is the user refueling order information sent from the client, the specific processing procedure of the processing server in step 103 includes: the server is further capable of performing:

and step H1, receiving user refueling order information sent by the client, wherein the refueling order information comprises target petroleum commodities, position information of the client, a target gas station and a refueling time period.

If the user needs to refuel, the corresponding refuel key or voice in the APP or the applet on the client can be triggered to trigger the corresponding refuel service, so as to form the user refuel order information.

And step H2, extracting the position information of the client in the user oiling order information, searching the position information of the target gas station in the map, and calculating the time consumption of the client in reaching the target gas station.

The route from the position of the client to the position of the target gas station is calculated according to the position information of the client and the position information of the target gas station, and then the time consumption of the vehicle journey is calculated according to the route and the average time of each vehicle passing through the route.

And step H3, if the current time and the latest time point of the vehicle journey time consumption are less than or equal to the refueling time period, acquiring whether a target petroleum commodity of the target gas station in the refueling time period has a residual oil outlet, if so, transmitting user refueling order information to a gas station end of the target gas station for confirmation receiving, generating a confirmation receiving instruction and transmitting the confirmation receiving instruction to a client, otherwise, refusing to receive the user refueling order information, and generating a refusing receiving instruction and transmitting the refusing instruction to the client.

If the calculated vehicle journey time is added with the latest time point of the current time less than or equal to the refueling time period, the user is proved to be capable of reaching the gas station for refueling in the refueling time period. In this case, if the pick-up amount of the target petroleum commodity corresponding to the fueling station in the fueling period has reached the maximum pick-up amount, there is no remaining fuel outlet, and it is proved that the fueling period is not possible for the user to perform fueling even if the user arrives at the fueling station. Correspondingly generating a refusal receiving instruction, wherein the refusal receiving instruction comprises other time periods which can be accepted by the target petroleum commodity. Thus, after the client receives the absolute receiving instruction, the user can reselect other time periods to refuel according to the actual conditions of the gas station. Or the user can select other gas stations to refuel, and the selection and determination are specifically performed according to the actual needs of the user.

And step H4, if the current time and the vehicle journey time are more than the latest time point of the refueling time period, refusing to receive the user refueling order information, generating a command for reconfirming the refueling time period, and sending the command to the client.

If the current time and the time consumption of the vehicle journey are greater than the latest time point of the refueling time period, the user is proved to be unable to arrive at the refueling time period, so that the server automatically refuses to receive the refueling order information, acquires other time periods which can be used for receiving orders of the target petroleum commodity of the refueling station, adds the time periods to the command of reconfirming the refueling time period, and sends the command to the client side so that the user can reselect other time periods to refuel according to the actual condition of the refueling station. Or the user can select other gas stations to refuel, and the selection and determination are specifically performed according to the actual needs of the user.

Through the scheme, the server can process the oiling order information of the user in advance, timely inform the user of some oiling order information which cannot be completed at all, enable the user to timely change the oiling order, and reduce the situation that oiling is impossible due to incapability of reaching a filling station in time.

In a specific extension, if the petroleum operation data is a command for entering a fuel station sent by the client, the processing server is further capable of executing:

And step J1, receiving a command of entering a filling station from the client and acquiring the position information of the client.

In this step, the user wants to select a common filling station as a parking filling station, and the user can trigger a key of the parking filling station on the client to correspondingly form a parking filling station command, so that the client can send the parking filling station command to the server. After the server receives the information, the server acquires the position information of the client, and then searches the corresponding gas station according to the position of the client.

The location information of the client may be current location information of the client or location information of a residence preset by a user.

And step J2, determining at least one gas station with a distance smaller than or equal to a distance threshold according to the position information of the client, and sending the at least one gas station to the client so that the client can select from the at least one gas station.

And step J3, receiving the selected target parking station sent by the client, integrating the target parking station with a parking station command, and sending the integrated information to a gas station end corresponding to the target parking station so that the gas station end can establish parking connection with the client through the server.

In the step, after the integrated information is sent to the gas station end corresponding to the target parking station, the parking connection can be established at the client after the gas station end receives the integrated information, so that the gas station end can directly send the corresponding discount information or preferential information to the client in time.

In addition, after the filling station end establishes a resident connection with the client, a resident success instruction is sent to the server, and the server stores the resident filling station into a resident cache library corresponding to the client. And meanwhile, the related information of the client is stored in a resident user buffer library corresponding to the gas station.

Each gas station can also adopt preferential or discount for each resident user, and specific preferential or discount measures are selected according to the actual condition of each gas station. The user can enter the homepage of the gas station through the APP or the applet on the client, and the corresponding preferential information is checked in the homepage.

The number of the parking stations selected by the user can be one or more, so that if the corresponding parking station issues new petroleum information, the new petroleum information is displayed in the information recommendation field of the corresponding display screen.

The parking stations can be displayed in the corresponding parking station columns of the user clients, the displaying sequence can be arranged in sequence according to the distance from the current position of the user, the selected parking time, the access quantity, the order quantity and the like, and the user can select the corresponding arrangement mode according to the actual needs of the user.

Through the scheme, the function of selecting the parking station can be provided for the user through the server, so that the user can conveniently and timely check some petroleum information and some preferential information issued by the corresponding parking station, and convenience is provided for the user.

In addition, as a supplement to the solution of this embodiment, if the petroleum running data is an invoice request instruction sent from the client, the specific processing procedure of the processing server in step 103 includes:

and step K1, receiving an invoice request instruction sent by the client.

And step K2, searching corresponding petroleum order information and an invoicing record of the corresponding petroleum order information from a storage database of the corresponding gas station account according to the invoice request instruction.

And step K3, if the billing record is empty, acquiring the amount data of the petroleum order information from a storage database of the corresponding gas station account, extracting the billing account information in the invoice request instruction, correspondingly generating electronic invoice information, transmitting the electronic invoice information to the client, and if the corresponding electronic invoice information exists in the billing record, generating a refusing billing instruction and transmitting the refusing billing instruction to the client.

In the above scheme, if the user wants to invoice, the user can choose to send an invoice request instruction to the gas station end through the APP or applet of the user end, and then corresponding electronic invoice is issued. The method comprises the following steps:

And after the existence of the corresponding transaction is determined from a storage database of the corresponding gas station account number and the transaction is successful, checking whether the transaction has issued invoice information, if not, issuing corresponding invoice information according to the transaction amount and the issuing information carried in the corresponding invoice request instruction, and sending the invoice information to the client for display.

Through the technical scheme, the intelligent invoicing function and the function of counting various data information are provided for the user, so that the use of the user can be more convenient.

Based on the above embodiment corresponding to fig. 1, this implementation proposes a network-based petroleum operation data processing apparatus, as shown in fig. 2, including:

a receiving module 21, configured to receive petroleum operation data information sent by a client through the internet or a virtual private network, where the client is a user end and/or a gas station end;

The checking module 22 is used for performing security check on the petroleum operation data, intercepting the petroleum operation data if the petroleum operation data contains dangerous information, and otherwise, releasing the petroleum operation data;

the processing module 23 is used for transmitting the released petroleum operation data to the processing server for processing through the NAT gateway and the router;

and the storage module 24 is used for programming the data processed by the processing server by using the structured query language and storing the data in the database server.

In a specific embodiment, if the petroleum operation data is the published petroleum information sent from the gas station, the processing module 23 is specifically configured to:

transmitting the released release oil product information to a processing server through the NAT gateway and the router; the processing server inputs the released oil product information into an oil product category identification model for processing, and outputs the released oil product category corresponding to the released oil product information, wherein the oil product category identification model is obtained by training a neural network by utilizing sample oil product information of a pre-marked oil product category; the processing server searches corresponding target auditing standards in the memory according to the issued oil categories, wherein auditing standards corresponding to the oil categories are stored in the memory in advance; the processing server checks all parameters of the released oil product information according to the target auditing standard, and if the checking is successful, the released oil product information is used as processed data;

The apparatus further comprises:

and the sending module is used for pushing the programmed data stored in the database server to an account platform corresponding to the gas station end for release.

In a specific embodiment, the processing module 23 is specifically further configured to:

acquiring a preset number of sample oil information, and adding a corresponding oil category label for each sample oil information, wherein each sample oil information comprises a plurality of oil information data; pre-constructing an oil product identification initial neural network with an oil product identification input layer, N oil product identification hidden layers and an oil product identification output layer, wherein the construction number N of the oil product identification hidden layers is more than or equal to the number maximum value X of oil product information data in sample oil product information; inputting sample oil information from an oil identification input layer, and processing the sample oil information through N oil identification hidden layers, wherein the first oil identification hidden layer receives data content output from the oil identification input layer, and the data of the rest oil identification hidden layers are all data content output after the last oil identification hidden layer is processed; the last oil product identification hidden layer outputs the processing result data to the oil product identification output layer so as to ensure that the oil product identification output layer determines the corresponding output oil product type according to the processing result data; judging whether the output oil product type is the same as the corresponding oil product type label, if so, training next sample oil product information, and if not, adjusting parameters of each oil product identification hidden layer to enable the output oil product type to be the same as the corresponding oil product type label; and taking the oil product identification initial neural network after the sample oil product information is completely trained as an oil product identification model, and storing the oil product identification model into a processing server.

In a specific embodiment, if the petroleum operation data is information to be distributed about petroleum knowledge sent from a gas station side and/or a user side, the processing module 23 is specifically further configured to:

transmitting the released information to be released of the petroleum knowledge to a processing server through the NAT gateway and the router; the processing server inputs the information to be issued of the petroleum knowledge into a knowledge category identification model for processing, and outputs the knowledge category to be issued corresponding to the information to be issued of the petroleum knowledge, wherein the knowledge category identification model is obtained by training a neural network by utilizing sample petroleum knowledge information of a pre-marked knowledge category; the processing server marks the information to be distributed of the petroleum knowledge by utilizing the category of the knowledge to be distributed, and takes the marked information to be distributed of the petroleum knowledge as processed data.

And the sending module is also used for pushing the programmed data stored in the database server to the account platform corresponding to the gas station end and/or the user end for release.

acquiring a preset number of sample petroleum knowledge information, and adding a corresponding knowledge category label for each sample petroleum knowledge information; a knowledge identification initial neural network with a knowledge identification input layer, M knowledge identification hidden layers and a knowledge identification output layer is constructed in advance, wherein each knowledge identification hidden layer correspondingly identifies the coincidence probability of one knowledge category, and the construction quantity M of the knowledge identification hidden layers is more than or equal to the category quantity maximum value Q of the knowledge category in the sample petroleum knowledge information; inputting the sample petroleum knowledge information from a knowledge identification input layer, and extracting keywords from the sample petroleum knowledge information by the knowledge identification input layer; the knowledge identification input layer inputs the extracted keywords into each knowledge identification hidden layer for processing, and each knowledge identification hidden layer correspondingly outputs probability P belonging to the corresponding knowledge category ₁ ，P ₂ ，……，P _M And respectively sending the information to a knowledge identification output layer; the knowledge identification output layer screens out the knowledge category corresponding to the maximum value of the probability of the knowledge category as an output knowledge category, judges whether the output knowledge category is the same as the corresponding knowledge category label, if so, trains the petroleum knowledge information of the next sample, otherwise, adjusts the parameters of the knowledge identification hidden layer corresponding to the knowledge category label so that the probability of the knowledge category output after processing is 100%, and trains the petroleum knowledge information of the next sample; knowledge identification after complete training of sample petroleum knowledge informationThe initial neural network serves as a knowledge category identification model, and the knowledge category identification model is stored in the processing server.

In a specific embodiment, if the oil operation data information is order data of successful transaction at the gas station end within a set period of time, the processing module 23 is specifically further configured to:

transmitting order data of successful released transaction to a processing server through an NAT gateway and a router; the processing server calculates the cost and the sum of the order data of each successful transaction according to the petroleum type and the petroleum amount in the order data of the successful transaction; calculating corresponding profit amount according to the cost amount and the transaction amount of the order data of each transaction success, and establishing a coordinate system by taking the profit amount as a vertical axis and the corresponding time as a horizontal axis; the processing server analyzes the coordinate system, determines the corresponding operation state, and takes the operation state as processed data, specifically: if the coordinate system is the overall ascending trend, the account corresponding to the gas station end is determined to belong to ascending type operation, if the coordinate system is the up-and-down fluctuation trend, the account corresponding to the gas station end is determined to belong to stable type operation, and if the coordinate system is the overall descending trend, the account corresponding to the gas station end is determined to belong to descending type operation.

And the sending module is also used for pushing the programmed data stored in the database server to the gas station end for display.

In an embodiment, if the petroleum operation data is a petroleum inspection instruction sent from the user side and/or the gas station side, the processing module 23 is further specifically configured to:

transmitting the released oil product inspection instruction to a processing server through an NAT gateway and a router, wherein the oil product inspection instruction contains oil types; the processing server extracts the petroleum types in the petroleum type inspection instruction, and searches at least one inspection station to be determined, which has petroleum type inspection qualification, from the map; the processing server acquires the position information of the user side and/or the gas station side, and searches for a determination inspection station which belongs to the same city level with the position information from at least one inspection station to be determined; if a plurality of the found definite inspection stations are arranged according to the sequence of going far from the position information, the distance is sent to a user side and/or a gas station side so that the user side and/or the gas station side can select a target inspection station from the plurality of definite inspection stations; the processing server receives the released target inspection station and the released delivery time sent by the user side and/or the gas station side through the Internet or the virtual private network, acquires whether the delivery service corresponding to the petroleum type of the target inspection station in the delivery time is saturated or not, generates a refusing delivery instruction to send to the user side and/or the gas station side if the delivery service is saturated, so that the user side and/or the gas station side can re-determine the target inspection station, packages the oil product inspection instruction and the delivery time if the delivery service is not saturated, and takes the packaged data as processed data.

The sending module is further configured to send the programmed data stored in the database server to the target inspection station.

In order to achieve the above object, based on the above embodiment of the method shown in fig. 1 and the embodiment of the apparatus shown in fig. 2, the embodiment of the present application further provides an electronic device, as shown in fig. 3, including a memory 32 and a processor 31, where the memory 32 and the processor 31 are both disposed on a bus 33, and the memory 32 stores a computer program, and the processor 31 implements the network-based petroleum operation data processing method shown in fig. 1 when executing the computer program.

Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile memory (may be a CD-ROM, a usb disk, a mobile hard disk, etc.), and includes several instructions for causing an electronic device (may be a personal computer, a server, or a network device, etc.) to perform the methods described in various implementation scenarios of the present application.

Optionally, the device may also be connected to a user interface, a network interface, a camera, radio Frequency (RF) circuitry, sensors, audio circuitry, WI-FI modules, etc. The user interface may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (e.g., bluetooth interface, WI-FI interface), etc.

It will be appreciated by those skilled in the art that the structure of an electronic device provided in this embodiment is not limited to the physical device, and may include more or fewer components, or may combine certain components, or may be arranged in different components.

Based on the embodiment of the method shown in fig. 1 and the device shown in fig. 2, correspondingly, the embodiment of the application also provides a storage medium, on which a computer program is stored, which when being executed by a processor, implements the network-based petroleum operation data processing method shown in fig. 1.

The storage medium may also include an operating system, a network communication module. An operating system is a program that manages the hardware and software resources of an electronic device, supporting the execution of information handling programs, as well as other software and/or programs. The network communication module is used for realizing communication among all components in the storage medium and communication with other hardware and software in the electronic device.

From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general hardware platforms, or may be implemented by hardware.

By applying the technical scheme, the petroleum operation data sent by the user side and/or the gas station side through the Internet or the virtual private network is subjected to security check, after no dangerous information is determined, the petroleum operation data is transmitted to the processing server through the NAT gateway and the router to be further processed according to the specific content of the petroleum operation data, and the processing result is programmed by utilizing a structured query language and stored in the database server. Thus, the safety of the petroleum operation data can be ensured, and the processing speed of the petroleum operation data can be accelerated.

Those skilled in the art will appreciate that the drawings are merely schematic illustrations of one preferred implementation scenario, and that the modules or flows in the drawings are not necessarily required to practice the present application. Those skilled in the art will appreciate that modules in an apparatus in an implementation scenario may be distributed in an apparatus in an implementation scenario according to an implementation scenario description, or that corresponding changes may be located in one or more apparatuses different from the implementation scenario. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.

The foregoing application serial numbers are merely for description, and do not represent advantages or disadvantages of the implementation scenario. The foregoing disclosure is merely a few specific implementations of the present application, but the present application is not limited thereto and any variations that can be considered by a person skilled in the art shall fall within the protection scope of the present application.

Claims

1. A network-based petroleum operation data processing method, comprising the steps of:

programming the data processed by the processing server by utilizing a structured query language and storing the data in a database server;

if the petroleum operation data is the published petroleum information sent from the gas station end, the released petroleum operation data is transmitted to a processing server for processing through a NAT gateway and a router, and the method specifically comprises the following steps:

pushing the programmed data stored in the database server to an account platform corresponding to the gas station end for release;

before the processing server inputs the released oil product information into the oil product category identification model for processing and outputs the released oil product category corresponding to the released oil product information, the processing server specifically comprises:

2. The network-based petroleum operation data processing method according to claim 1, wherein if the petroleum operation data is information to be distributed of petroleum knowledge sent from a gas station side and/or a user side, the step of transmitting the released petroleum operation data to a processing server for processing through a NAT gateway and a router specifically comprises:

the processing server inputs the information to be distributed of the petroleum knowledge into a knowledge category identification model for processing, and outputs the information

The knowledge category to be issued corresponding to the information to be issued of the petroleum knowledge is issued, wherein the knowledge category identification model is obtained by training a neural network by utilizing sample petroleum knowledge information of a pre-marked knowledge category;

3. The network-based petroleum operation data processing method according to claim 2, wherein before the processing server inputs the petroleum knowledge to be distributed information into a knowledge category identification model for processing, outputting a knowledge category to be distributed corresponding to the petroleum knowledge to be distributed information, specifically comprising:

the knowledge identification input layer inputs the extracted keywords into each knowledge identification hidden layer for processing, and each knowledge identification hidden layer correspondingly outputs probability P belonging to the corresponding knowledge category ₁ ，

P ₂ ，……，P _M And respectively sending the knowledge identification output layers;

4. The network-based petroleum operation data processing method according to claim 1, wherein if the oil operation data information is order data of successful transaction at a gas station end in a set period of time, the transferring the released petroleum operation data to a processing server for processing through a NAT gateway and a router specifically comprises:

5. The network-based petroleum operation data processing method according to claim 1, wherein if the petroleum operation data is an oil inspection instruction sent from a user side and/or a gas station side, the step of transmitting the released petroleum operation data to a processing server for processing through a NAT gateway and a router specifically comprises:

6. A network-based petroleum operation data processing apparatus, comprising:

the storage module is used for programming the data processed by the processing server by utilizing a structured query language and storing the data into the database server;

if the petroleum operation data is the published petroleum information sent from the gas station end, the processing module is specifically configured to:

The apparatus further comprises:

the sending module is used for pushing the programmed data stored in the database server to an account platform corresponding to the gas station end for release;

the processing module is specifically further configured to:

7. An electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the network-based petroleum operational data processing method of any one of claims 1 to 5.

8. A storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the network-based petroleum operational data processing method of any one of claims 1 to 5.