CN112508652A

CN112508652A - Server-side-based petroleum data processing method and device and storage medium

Info

Publication number: CN112508652A
Application number: CN202011471455.3A
Authority: CN
Inventors: 裴修尧; 杜彪; 佟力; 鲁冰; 朱云鹏; 钟子豪
Original assignee: Beijing Yixingyuan Petrochemical Technology Co ltd
Current assignee: Beijing Yixingyuan Petrochemical Technology Co ltd
Priority date: 2020-12-14
Filing date: 2020-12-14
Publication date: 2021-03-16

Abstract

The embodiment of the invention discloses a server-side-based petroleum data processing method, a server-side-based petroleum data processing device and a server-side-based petroleum data processing storage medium. Therefore, the server can automatically recommend the oil information for the user, and the recommended oil information is more in line with the actual requirements of the user or the vehicle of the user, so that convenience is provided for the user.

Description

Server-side-based petroleum data processing method and device and storage medium

Technical Field

The invention belongs to the technical field of data processing, and particularly relates to a server-side-based petroleum data processing method, a server-side-based petroleum data processing device and a storage medium.

Background

Traditional filling station refuels service, the procedure is complicated, and the process is redundant slowly, needs the user to drive the car into filling station back usually, selects again to add the oil number, refuels amount of money etc. waits to refuel and finishes, still needs to settle accounts through modes such as cash payment, cash change, has caused a large amount of time wastes. If the passenger flow of the gas station is overlarge, the congestion of the vehicles behind can be caused, the refueling efficiency is reduced, and the negative influence is brought to the operation of the gas station.

Based on the situation, a plurality of APP client services corresponding to the gas stations are available at present, and are used for providing the service of ordering and refueling for the gas stations.

However, the existing online oil filling service is relatively limited, a user needs to search for a corresponding oil service to order, oil information cannot be intelligently recommended for the user, and the online oil filling service is inconvenient to use.

Disclosure of Invention

In view of the above problems, the invention provides a server-side-based petroleum data processing method, a server-side-based petroleum data processing device and a server-side-based petroleum data processing storage medium, so as to overcome the technical problems that a user needs to search for a corresponding petroleum service to place an order, cannot intelligently recommend petroleum information for the user, and is inconvenient to use.

According to the first aspect of the invention, a server-side-based oil data processing method is provided, and the steps comprise:

acquiring corresponding display information according to role authority information in an account login instruction sent by a received client, and sending the display information to the corresponding client, wherein the client comprises: a user side or a fueling station side;

the method comprises the steps of receiving owner information and/or vehicle information sent by a client, and determining a first to-be-pushed petroleum type according to the owner information and/or the vehicle information by utilizing a pre-established information recognition neural network model;

receiving petroleum order data sent by a client, and determining a second petroleum type to be pushed according to the petroleum order data by using a pre-constructed order recognition neural network model;

and determining at least one target petroleum information by combining the first to-be-pushed petroleum type and the second to-be-pushed petroleum type, and sending the target petroleum information to a client for display.

Further, the method further comprises:

receiving an oil product inspection instruction sent by a client, wherein the oil product inspection instruction contains a petroleum type;

extracting the oil type in the oil product inspection instruction, and searching at least one inspection station to be determined with the oil type inspection qualification from a map;

obtaining the position information of the client, and searching a determined 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 determined inspection stations are arranged, the plurality of the determined inspection stations are arranged according to the sequence of the distance from the position information of the client to the far position and then are sent to the client, so that the client can select a target inspection station from the plurality of the determined inspection stations;

receiving a target inspection station and submission time sent by the client, acquiring whether submission service corresponding to the petroleum type in the submission time of the target inspection station is saturated, if so, generating a submission rejection instruction to be sent to the client so that the client can determine the target inspection station again, and if not, packaging the oil product inspection instruction and the submission time and sending the packaged oil product inspection instruction and submission time to the target inspection station.

Further, the obtaining of the corresponding display information according to the received role authority information in the account login instruction sent by the client and the sending of the display information to the corresponding client specifically include:

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

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

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

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

Further, before the vehicle owner information and/or the vehicle information sent by the receiving client, and the first petroleum type to be pushed is determined according to the vehicle owner information and/or the vehicle information by using a pre-constructed information recognition neural network model, the method further comprises the following steps:

acquiring a preset amount 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 the petroleum type tags being one or more;

pre-constructing an information recognition initial neural network, wherein the information recognition initial neural network comprises: the system comprises an information identification input layer, N information identification hidden layers and an information identification output layer;

inputting the information sample data from an information identification input layer, and processing the information sample data through the 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 receive data content output after the last information identification hidden layer is processed;

the last information identification hidden layer outputs the processing result data to an information identification output layer so that the information identification output layer can determine the corresponding petroleum type according to the processing result data;

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

and (4) taking the information identification initial neural network after all information sample data are trained as an information identification neural network model.

Further, before the receiving client sends oil order data and a second petroleum type to be pushed is determined according to the oil order data by using a pre-constructed order recognition neural network model, the method further comprises the following steps:

acquiring preset quantity of petroleum order sample data, and adding a corresponding petroleum type label for each petroleum order sample data, wherein the quantity of the petroleum type labels is one or more;

pre-constructing an order identification initial neural network, wherein the order identification initial neural network comprises: the system comprises an order identification input layer, M order identification hidden layers and an order identification output layer;

inputting the petroleum order sample data from an order identification input layer, and processing the petroleum order sample data through the 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 of the order identification hidden layers are data content output after the last order identification hidden layer is processed;

the last order identification hidden layer outputs the processing result data to an order identification output layer, so that the order identification output layer determines the corresponding petroleum type according to the processing result data;

judging whether the output petroleum type is the same as the corresponding petroleum type label, if so, training the sample data of the next petroleum order, if not, calculating an order loss function according to the output petroleum type and the corresponding petroleum type label, and adjusting the parameters of the hidden layer for order recognition according to the order loss function to ensure that the output petroleum type is the same as the corresponding petroleum type label;

and taking the order recognition initial neural network after the petroleum order sample data is completely trained as an order recognition neural network model.

Further, the method further comprises:

receiving user refueling ordering information sent by a client, wherein the refueling ordering information comprises a target petroleum commodity, position information of the client, a target gas station and a refueling time period;

extracting the position information of the client in the information of ordering the user to refuel, searching the position information of the target gas station in a map, and calculating the time consumed by the client to reach the target gas station;

if the current time plus the vehicle journey consumed time is not more than the latest time point of the refueling time period, acquiring whether the target petroleum commodity of the target gas station has a residual oil outlet in the refueling time period, if so, sending the refueling order information of the user to a refueling station end of the target gas station for confirmation receiving, and simultaneously generating a confirmation receiving instruction to send to a client, otherwise, refusing to receive the refueling order information of the user, generating a refusing receiving instruction to send to the client;

and if the current time plus the vehicle journey consumed time is larger than the latest time point of the refueling time period, refusing to receive the refueling and ordering information of the user, generating a re-confirmation refueling time period instruction and sending the re-confirmation refueling time period instruction to the client.

Further, the method further comprises:

receiving a command of entering a gas station sent by the client to acquire the position information of the client;

determining at least one gas station with the distance less 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;

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

According to a second aspect of the present invention, a server-side petroleum data processing device is provided, comprising:

the receiving module is used for acquiring corresponding display information according to the received role authority information in the account login instruction sent by the client, and sending the display information to the corresponding client, wherein the client comprises: a user side or a fueling station side;

the information identification module is used for receiving owner information and/or vehicle information sent by a client side, and determining a first to-be-pushed petroleum type according to the owner information and/or the vehicle information by utilizing a pre-established information identification neural network model;

the order identification module is used for receiving petroleum order data sent by the client and determining a second petroleum type to be pushed according to the petroleum order data by utilizing a pre-established order identification neural network model;

and the combination module is used for combining the first to-be-pushed petroleum type and the second to-be-pushed petroleum type to determine at least one piece of target petroleum information and sending the target petroleum information to a client for display.

According to a third aspect of the present invention, an electronic device is provided, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the server-side petroleum data processing method according to the first aspect when executing the computer program.

According to a fourth aspect of the present invention, a storage medium is proposed, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the steps of the server-side based oil data processing method of the first aspect.

The server-side-based petroleum data processing method, device and storage medium provided by the embodiment of the invention have the following beneficial effects:

according to the technical scheme, the pre-established information recognition neural network model can be used for determining the first petroleum type to be recommended according to the owner information and the vehicle information sent by the client, and the pre-established order recognition neural network model is used for determining the second petroleum type to be recommended according to the petroleum order data stored in the client, so that the server can combine the two petroleum types to be recommended to determine the target petroleum information matched with the user and the vehicle of the user, and the target petroleum information is sent to the client to be displayed in the information recommendation column of the corresponding display screen. Therefore, the server can automatically recommend the oil information for the user, and the recommended oil information is more in line with the actual requirements of the user or the vehicle of the user, so that convenience is provided for the user.

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 will be more clearly understood from the following detailed description, taken with reference to the accompanying drawings, in which:

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

FIG. 2 is a block diagram of a fueling station-based oil data processing apparatus 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 portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.

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

Techniques, methods, and apparatus known to those 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 numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

As shown in fig. 1, this embodiment provides a server-side-based oil data processing method, which is applicable to a server side, where the server side belongs to a service platform that is set up in advance and performs centralized processing on fueling data sent from a user side and/or a fueling station side, and the user side and the fueling station side need to use the service platform to perform fueling data processing, and need to install corresponding APPs at the user side and the fueling station side in advance or install corresponding applets in instant messaging.

The method comprises the following steps:

step 101, obtaining corresponding display information according to role authority information in an account login instruction sent by a received client, and sending the display information to the corresponding client, wherein the client comprises: a user side or a fueling station side.

When the individual user opens the corresponding APP or the applet on the user terminal for the first time, the individual account is established first, the corresponding user role is selected, and the individual user or the gas station user can be selected.

When the individual user is selected, an account registration interface pops up. And inputting a user name and a password, packaging the user name, the password and the selected user role, and sending the user name, the password and the selected user role to a server, matching a corresponding user interface according to the user role by the server, and establishing a corresponding storage database for the corresponding personal account so as to store the data information of the personal account. The data of each individual user in the server is correspondingly stored in an individual user memory, and the individual user memory comprises a storage database corresponding to each individual account.

When a gas station user is selected, an account registration interface is popped up. The method comprises the steps of inputting a name and a password of the refueling station, packaging and sending the name and the password of the refueling station and the selected role of the refueling station to a server, matching a corresponding interface of the refueling station by the server according to the role of the refueling station, and establishing a corresponding storage database for a corresponding account number of the refueling station so as to store data information of the account number of the refueling station. The data of each gas station user in the server are 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 personal user or the gas station personnel logs in again through the user terminal or the gas station terminal, an account login instruction is sent to the server, and the account login instruction comprises role authority information, an account name, a password and some basic information corresponding to the client terminal.

And after the server receives the account login instruction, if the role authority information is the personal user, calling the related display information in the storage database of the corresponding personal account from the personal user storage. And if the service station user is the service station user, calling related display information in a storage database corresponding to the service station account from a storage of the service station user. And sending the corresponding display information to the corresponding client for display.

And 102, receiving owner information and/or vehicle information sent by a client, and determining the type of the first petroleum to be pushed according to the owner information and/or the vehicle information by utilizing a pre-constructed information recognition neural network model.

In the step, the information recognition neural network model is obtained by utilizing a large amount of owner information and/or vehicle information with the specific required petroleum type through learning and training of the neural network, and can be processed according to the owner information and/or the vehicle information to obtain the first petroleum type to be pushed, which is correspondingly required.

The vehicle owner information includes: name, age, gender, personal preferences, weight, etc., and the vehicle information includes: vehicle type, brand, displacement, vehicle model, color, etc.

The information identification input layer of the corresponding information identification neural network model comprises two types of input ports: the vehicle owner information input port and the vehicle information input port input the received vehicle owner information and/or vehicle information from the corresponding input ports, and after the data processing is carried out through the information identification input layer, the character data is converted into code data so that the information identification hidden layer of the information identification neural network model can carry out further information processing according to the data. And finally obtaining the corresponding first type of petroleum to be pushed.

And 103, receiving petroleum order data sent by the client, and determining a second petroleum type to be pushed according to the petroleum order data by using a pre-constructed order recognition neural network model.

In this step, the petroleum order data is historical order data of the corresponding user, and the order data includes: the position of the gas station, the type of refueling, the refueling amount, the refueling time and other information.

The order recognition neural network model is obtained by performing learning training on the neural network according to multiple groups of petroleum order data serving as samples, wherein each group of petroleum orders are multiple order data of the same user.

The order identification input layer of the order identification neural network model comprises a plurality of input ports, and each input port can input order data. The number of input ports is greater than or equal to the maximum order data number. To ensure that multiple order data can be input simultaneously. And the order identification input layer performs data conversion processing on the order data to convert the order data into code data, so that the order identification hidden layer of the order identification neural network model can be processed according to the code data, and finally the corresponding second petroleum type to be pushed is obtained.

And 104, determining at least one target petroleum information by combining the first to-be-pushed petroleum type and the second to-be-pushed petroleum type, and sending the target petroleum information to the client for display.

The oil information is the oil information issued by the corresponding gas station merchant so that each vehicle owner can choose to purchase the oil filling service.

In the above steps, the server can search corresponding petroleum information according to the first petroleum type to be pushed and the second petroleum type to be pushed, P petroleum information are searched, and the server can select Q petroleum information which is close to the user as target petroleum information according to the current position of the user. P is more than or equal to Q, and P and Q are positive integers. After the server sends the target petroleum information to the user side, the target petroleum information can be displayed on a display screen of the user side. The information recommendation column of the display screen can be arranged at the middle lower part of the whole screen, can be displayed in a mode that target petroleum information is expanded one by one, and can also be displayed in a mode that message notification is scrolled one by one. The specific display mode user can select and set according to own preference and needs. In addition, the displayed sequence can be sorted according to the distance, the amount, the issuing time, the sales volume, the good rating and the like. The specific sorting mode can also be selected according to the actual needs of the user.

According to the scheme, the pre-constructed information recognition neural network model can be used for determining the first petroleum type to be recommended according to the vehicle owner information and the vehicle information sent by the client, and the pre-constructed order recognition neural network model is used for determining the second petroleum type to be recommended according to the petroleum order data stored in the client, so that the server can combine the two petroleum types to be recommended to determine the target petroleum information matched with the user and the vehicle of the user, and the target petroleum information is sent to the client to be displayed in the information recommendation column corresponding to the display screen. Therefore, the server can automatically recommend the oil information for the user, and the recommended oil information is more in line with the actual requirements of the user or the vehicle of the user, so that convenience is provided for the user.

In a particular embodiment, the method further comprises:

step A1, receiving an oil product inspection instruction sent by a client, wherein the oil product inspection instruction comprises the oil type.

If the client is a refueling station end, the refueling station may need to put some branded oil or some high-quality oil on the shelf, but the oil quality of the branded oil or the high-quality oil needs to be verified and confirmed through a checking station. However, since the corresponding inspection service of the inspection station may be busy, in order to facilitate this process and avoid time waste, the fueling station end may perform the search and determination through the server.

And if the refueling station terminal wants to check the oil K of a certain type, sending an oil checking instruction to the server.

And A2, extracting the oil type in the oil inspection instruction, and searching at least one inspection station to be determined with oil type inspection qualification from the map.

In this step, the map is a geographical location map of each inspection station having oil inspection qualification. And marking the corresponding oil type of the inspection qualification on each inspection station in the map in advance, so that the corresponding search can be carried out in the map according to the oil type in the oil inspection instruction.

Step A3, obtaining the position information of the client, and searching for the determined checkpoint belonging to the same city level with the position information from at least one checkpoint to be determined.

In this step, for a certain fueling station terminal, only the inspection result from the local inspection station may be valid, so that the inspection station corresponding to the local city level organization needs to be correspondingly searched as the determined inspection station of the fueling station terminal. One or more of the identified verification checkpoints may be found.

In addition, if the corresponding definite inspection station can not be found in the same city level, the definite inspection station of province level is searched in an enlarged range, and if the corresponding definite inspection station can not be found in the province level, the definite inspection station in the whole country is searched.

Step A4, if there are multiple found check stations, arranging the check stations according to the sequence of the distance from the position information of the client to the far position, and sending the check stations to the client, so that the client can select a target check station from the multiple check stations.

In the step, if one found check station is determined, the check station is directly sent to the client side for the gas station user to confirm at the client side. If a plurality of check stations are searched for, the user of the gas station needs to select according to the actual situation.

Step A5, receiving a target inspection station and delivery time sent by a client, acquiring whether the delivery service corresponding to the petroleum type of the target inspection station in the delivery time is saturated, if so, generating a delivery rejection instruction to be sent to the client so that the client can determine the target inspection station again, and if not, packaging the oil product inspection instruction and the delivery time and sending the packaged oil product inspection instruction and delivery time to the target inspection station.

In the step, after the oil product inspection instruction is sent to the target inspection station by the server, the 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. Therefore, the user of the gas station can mark the oil sample with the unique determination code and mail the oil sample to the target inspection station according to the corresponding mail information. And after receiving the oil product sample, the target inspection station judges whether the corresponding unique determination code is correct or not, if so, detects the oil product sample and issues a corresponding detection report. And uploading the detection report carrying the unique determination code to a server, determining the client of the corresponding gas station user by the server according to the unique determination code, and sending the detection report to the client for query and display.

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

In a specific embodiment, step 101 specifically includes:

step 1011, receiving an account login instruction sent by the client, and authenticating the account login instruction and the corresponding account information in the database.

In the step, a personal user or a gas station user wants to log in an account of the user, corresponding account information and an account password need to be input in an APP (application) or an embedded applet of a client, and the client maps and associates the account information and the account password to form an account login instruction and sends the account login instruction to a server.

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

Step 1012, after the authentication is successful, acquiring a corresponding Token signature, and combining the Token signature with the account login instruction to generate Token data.

The Token (Token, mark) is stored in a storage database of the server, unique Token signature data belonging to the account is stored in the storage database of the server, and the Token signature and the account login instruction are integrated together to generate the Token data.

And 1013, 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.

Among them, JWT (Jsonweb token, network data markup specification). The JWT data includes a header, a payload, and a signature, wherein the header is a corresponding file type, the payload is a data object (e.g., oil order data information of a user), and the like, and the signature is Token data, which is arranged as JWT data, and then the JWT data is transmitted to a corresponding client.

After receiving the JWT data, the APP or applet in the client extracts Token data therein and stores the Token data in a cookie repository in the client. Wherein the cookie repository is a database stored on the user's local terminal. And 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 basic request commands can be selected to generate the resource access request. The resource access request comprises: the method comprises the steps of personal information access, personal position information access, historical order information access and other information access requests corresponding to information which can be presented in an interface corresponding to an APP or an applet, and all the information access requests are concentrated in resource access requests.

The resource access request of the client contains corresponding Token data. After the resource access request is generated, in order to ensure the confidentiality of the resource access request, the resource access request needs to be encrypted in advance, wherein the Token data is not encrypted during encryption so as to be called and searched in a later period.

And then, the client extracts the Token data in the resource access request to search whether matched Token data exists in a cookie storage bank of the client, if so, the matching is proved to be successful, a configuration file stored in the local of 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 using the encryption key, and meanwhile, signature verification is carried out on the signature information and the Token data.

And after the client successfully decodes the resource access request and successfully verifies the signature, acquiring corresponding role authority information and sending the role authority information to the server.

And 1014, receiving the role authority information sent by the client to acquire corresponding display information, and sending the display information to the corresponding client.

Therefore, the server can acquire corresponding display information according to the role authority information. For example, some display contents required by the user targeted by the server and the contents stored in the database corresponding to the personal account are merged into the display information and sent to the client.

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

In a particular embodiment, prior to step 102, the method further comprises:

step B1, obtaining a predetermined amount 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 B2, pre-constructing an information identification initial neural network, wherein the information identification initial neural network comprises: the system comprises an information identification input layer, N information identification hidden layers and an information identification output layer.

And step B3, 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 the data content output from the information identification input layer, and the rest information identification hidden layers receive the data content output after the last information identification hidden layer is processed.

And step B4, the last information identification hidden layer outputs the processing result data to the information identification output layer, so that the information identification output layer determines the corresponding petroleum type according to the processing result data.

And step B5, judging whether the output petroleum type is the same as the corresponding petroleum type label, if so, training 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 step B6, using the information recognition initial neural network after all information sample data are trained as an information recognition neural network model.

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

The number of the information identification hidden layers can be set according to the number of information types in personal sample information or vehicle sample information, one information identification hidden layer correspondingly processes one type of sample information, then a processing result is transmitted to the next information identification hidden layer to be processed, the next information identification hidden layer combines the processing result of the previous information identification hidden layer with the processing result of the sample information of the type corresponding to the information identification hidden layer and then transmits the combined result to the next information identification hidden layer, and the like is carried out 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 character information of the corresponding 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 is different, the output result of the information identification initial neural network is proved to be incorrect, the information identification initial neural network needs to be adjusted, and the 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 labels, automatically adjusting each information identification hidden layer according to the loss function, and then reprocessing the information sample data by using the adjusted information identification initial neural network until the output result is consistent with the petroleum type labels.

After all information sample data are trained, detecting the trained information recognition initial neural network by using a preset amount of detection sample data, judging the accuracy rate of a recognition result, if the accuracy rate exceeds a corresponding threshold value, proving that the trained information recognition initial neural network meets the standard and can be used as an information recognition neural network model, if the accuracy rate is less than the corresponding threshold value, reselecting the information sample data, and training the information recognition initial neural network again until the obtained accuracy rate of the information recognition initial neural network exceeds the corresponding threshold value.

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

Through the scheme, the information identification neural network model can be used for identifying and judging the vehicle owner information and/or the vehicle information, and the corresponding first to-be-pushed petroleum type is determined so as to be recommended to the server according to the first to-be-pushed petroleum type.

In a particular embodiment, prior to step 103, the method further comprises:

and step C1, acquiring a preset amount of petroleum order sample data, and adding a corresponding petroleum type label for each petroleum order sample data, wherein the number of the petroleum type labels is one or more.

Step C2, pre-constructing an order identification initial neural network, wherein the order identification initial neural network comprises: the order recognition system comprises an order recognition input layer, M order recognition hidden layers and an order recognition output layer.

And step C3, inputting petroleum order sample data from the 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 of the order identification hidden layers are all data content output after the last order identification hidden layer is processed.

And step C4, the last order identification hidden layer outputs the processing result data to the order identification output layer, so that the order identification output layer determines the corresponding petroleum type according to the processing result data.

And C5, judging whether the output petroleum type is the same as the corresponding petroleum type label, if so, training the sample data of the next petroleum order, if not, calculating an order loss function according to the output petroleum type and the corresponding petroleum type label, and adjusting the parameters of the order identification hidden layer according to the order loss function so that the output petroleum type is the same as the corresponding petroleum type label.

And step C6, taking the order recognition initial neural network after the petroleum order sample data is completely trained as an order recognition neural network model.

In the above scheme, a plurality of input ports are included, and each input port can input order data. The number of input ports is greater than or equal to the maximum order data number. To ensure that multiple order data can be input simultaneously. The order identification input layer carries out 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 carry out processing according to the code data.

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

The number of the order identification hidden layers is consistent with that of the input ports, each order is processed by one order data correspondingly by the hidden layers, then the processing result is transmitted to the next order identification hidden layer to be processed, the next order identification hidden layer combines the processing result of the previous order identification hidden layer with the processing result of the order data corresponding to the order identification hidden layer and then transmits the combined result to the next order identification hidden layer, and the like are repeated 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 the character information of the corresponding 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 recognition initial neural network is different, the order recognition initial neural network is proved to be incorrect, the order recognition initial neural network needs to be adjusted, and the parameters of each order recognition 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 labels, 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 labels.

After all the order sample data are trained, detecting the trained order identification initial neural network by using a predetermined amount of detection sample data, judging the accuracy rate of the identification result, if the accuracy rate exceeds a corresponding threshold value, proving that the trained order identification initial neural network meets the standard and can be used as an order identification neural network model, if the accuracy rate is less than the corresponding threshold value, reselecting the information sample data, and training the order identification initial neural network again until the obtained accuracy rate of the order identification initial neural network exceeds the corresponding threshold value.

And using the final order identification initial neural network as an order identification neural network model.

By the scheme, the oil order data of the user can be identified and judged by the order identification neural network model, and the corresponding second petroleum type to be pushed is determined, so that the server can be combined to determine recommendation of oil information according to the first petroleum type to be pushed and the second petroleum type to be pushed.

In a particular embodiment, the method further comprises:

and D1, receiving the information of ordering the user by filling oil from the client, wherein the information of ordering the user by filling oil comprises the target petroleum commodity, the position information of the client, the target gas station and the oil filling time period.

Wherein, if user's vehicle need refuel, can trigger APP or the corresponding refuel button or the corresponding service of refueling of pronunciation trigger in the applet on the client, and then form the user and refuel the information of placing an order.

And D2, extracting the position information of the client in the information of ordering the user, searching the position information of the target gas station in the map, and calculating the time consumed by the client to reach the target gas station.

The method comprises the steps of marking in a map according to the position information of a client and the position information of a target gas station, calculating a route from the position of the client to the position of the target gas station, and further calculating the time consumed by the vehicle to travel according to the route and the average time of each vehicle passing through the route.

And D3, if the current time plus the bus trip consumption time is less than or equal to the latest time point of the refueling time period, acquiring whether the target petroleum commodity of the target refueling station has a residual oil outlet in the refueling time period, if so, sending the refueling order information of the user to the refueling station end of the target refueling station for confirmation and receiving, and simultaneously generating a confirmation receiving instruction to send to the client, otherwise, refusing to receive the refueling order information of the user, generating a refusing receiving instruction to send to the client.

And if the calculated time consumption of the vehicle journey and the latest time point when the current time is less than or equal to the refueling time period are added, the fact that the user can arrive at a refueling station within the refueling time period is proved to refuel. In this case, if the order quantity of the corresponding target petroleum commodity of the gas station in the refueling time period has reached the maximum order quantity and no oil outlet remains, it is proved that the refueling time period cannot be performed even if the user arrives at the gas station. And correspondingly generating a receiving refusing instruction, wherein the receiving refusing instruction comprises other available order time periods of the target petroleum commodity. Therefore, after the client receives the final receiving instruction, the user can reselect other time periods for refueling according to the actual situation of the gas station. Or the user can select other gas stations to refuel, and the selection is determined according to the actual needs of the user.

And D4, if the current time plus the bus trip consumption time is larger than the latest time point of the refueling time period, refusing to receive the refueling order information of the user, generating a re-confirmation refueling time period instruction and sending the re-confirmation refueling time period instruction to the client.

If the current time plus the vehicle journey consumed time is larger than the latest time point of the refueling time period, the fact that the user cannot arrive at the refueling station in the refueling time period is proved, the server automatically refuses to receive the refueling order placing information, obtains other time periods capable of receiving orders of the target petroleum commodity of the refueling station, adds the time periods into the refueling time period reconfirming instruction, and sends the instruction to the client side so that the user can reselect other time periods to refuel according to the actual situation of the refueling station. Or the user can select other gas stations to refuel, and the selection is determined according to the actual needs of the user.

Through the scheme, the server can process the refueling ordering information of the user in advance, and timely informs the user of the refueling ordering information which cannot be completed at all, so that the user can change the refueling ordering in time, and the condition that the refueling cannot be carried out due to the fact that the refueling station cannot be reached in time is reduced.

In a particular embodiment, the method further comprises:

and step E1, receiving the command of entering the gas station sent by the client, and acquiring the position information of the client.

In the step, the user wants to select a common gas station as a resident gas station, the user can correspondingly form a resident gas station command by triggering a resident gas station button on the client, and the client can send the resident gas station command to the server. And after receiving the position information, the server acquires the position information of the client, and further searches the corresponding gas station according to the position of the client.

The location information of the client may be the current location information of the client, or the location information of a place where the user has frequently set in advance.

And E2, determining at least one gas station with the distance less than or equal to the 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 E3, receiving the selected target stop-in gas station sent by the client, integrating the target stop-in gas station and stop-in gas station commands, and sending the integrated information to the corresponding stop-in terminal of the target stop-in gas station so that the stop-in terminal can establish stop-in connection with the client through the server.

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

In addition, after the filling station end establishes the parking connection with the client, a successful parking instruction is sent to the server, and the server stores the parked filling station into the parking cache library corresponding to the client. And meanwhile, storing the relevant information of the client into a resident user cache library corresponding to the refueling station.

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

One or more filling stations selected by the user can be selected, so that if the corresponding filling station publishes new petroleum information, the new petroleum information can be displayed in the information recommendation column of the corresponding display screen.

The resident gas station can also be displayed in a corresponding resident gas station column of the user client, the display sequence can be arranged in sequence according to the distance from the current position of the user, the selected resident time, the access amount, the order amount and the like, and the user can select the corresponding arrangement mode according to the actual requirement.

Through the scheme, the function of selecting the oil filling station to park can be provided for the user through the server, so that the user can check some petroleum information and some preferential information corresponding to the oil filling station to be published in time, and convenience is provided for the user.

In addition, as a supplement to the solution of the present embodiment, the method further includes:

in step F1, an invoice request command sent by the client is received.

And step F2, searching the corresponding oil order information and the corresponding invoicing record of the oil order information from the corresponding storage database of the gas station account according to the invoice request instruction.

And step F3, if the billing record is empty, acquiring the amount data of the petroleum order information from the corresponding storage database of the gas station account, extracting the billing account information in the invoice request instruction, correspondingly generating electronic invoice information, sending the electronic invoice information to the client, and if the billing record has the corresponding electronic invoice information, generating a billing rejection instruction and sending the billing rejection instruction to the client.

In the above scheme, if the user wants to invoice, the user can select to send an invoice request instruction to the refueling station end through the APP or applet of the user end, and issue a corresponding electronic invoice. The method specifically comprises the following steps:

the method comprises the steps that a user triggers an APP or an invoice issuing key in the petroleum commodity after transaction in an applet succeeds through a user side, an invoice request instruction is formed and sent to a server, wherein the invoice request instruction comprises information corresponding to a gas station, the server searches the corresponding gas station according to the information of the gas station, whether the corresponding transaction exists in a storage database of an account number of the corresponding gas station and after the corresponding transaction succeeds is determined, whether the transaction has issued invoice information or not is checked, if not, corresponding invoice information is issued according to the transaction amount and the invoice issuing information carried in the corresponding invoice request instruction, the invoice information is sent to the client side and displayed.

Through the technical scheme, the intelligent invoice issuing function and the function of counting various data information are provided for the user, so that the user can use the invoice more conveniently.

Based on the embodiment corresponding to fig. 1, the present embodiment proposes a server-side based oil data processing apparatus, as shown in fig. 2, including:

the receiving module 21 is configured to obtain corresponding display information according to the received role permission information in the account login instruction sent by the client, and send the display information to the corresponding client, where the client includes: a user side or a fueling station side;

the information identification module 22 is used for receiving owner information and/or vehicle information sent by the client, and determining a first to-be-pushed petroleum type according to the owner information and/or the vehicle information by utilizing a pre-established information identification neural network model;

the order identification module 23 is configured to receive oil order data sent by the client, and determine a second petroleum type to be pushed according to the oil order data by using a pre-established order identification neural network model;

and the combining module 24 is configured to determine at least one target petroleum information by combining the first to-be-pushed petroleum type and the second to-be-pushed petroleum type, and send the target petroleum information to the client for display.

In a specific embodiment, the apparatus further comprises: the oil product inspection module is specifically used for:

receiving an oil product inspection instruction sent by a client, wherein the oil product inspection instruction contains the type of petroleum; extracting the petroleum type in the oil product inspection instruction, and searching at least one inspection station to be determined with petroleum type inspection qualification from the map; obtaining the position information of a client, and searching a determined 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 determined inspection stations are arranged, the inspection stations are arranged according to the sequence of the distance from the position information of the client to the far position and then are sent to the client, so that the client can select a target inspection station from the plurality of the determined inspection stations; receiving a target inspection station and delivery time sent by a client, acquiring whether the delivery service corresponding to the petroleum type of the target inspection station in the delivery time is saturated, if so, generating a delivery refusing instruction to be sent to the client so that the client can determine the target inspection station again, and if not, packaging the oil product inspection instruction and the delivery time and sending the packaged oil product inspection instruction and delivery time to the target inspection station.

In a specific embodiment, the receiving module 21 is specifically configured to:

receiving an account login instruction sent by a client, and authenticating the account login instruction and corresponding account information in a database; after the authentication is successful, acquiring a corresponding Token signature, and combining the Token signature with an account login instruction to generate Token data; generating JWT data according to the Token data, and feeding back the JWT data to the client so that the client can determine corresponding role authority information according to the JWT data; and receiving the role authority information sent by the client to acquire corresponding display information, and sending the display information to the corresponding client.

In a specific embodiment, the apparatus further comprises: the information identification training module is specifically used for:

acquiring a preset amount 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 labels being one or more; pre-constructing an information identification initial neural network, wherein the information identification initial neural network comprises the following steps: the system comprises an information identification input layer, N information identification hidden layers and an information identification output layer; inputting information sample data from an 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 receive data content output after the last information identification hidden layer is processed; the last information identification hidden layer outputs the processing result data to the information identification output layer so that the information identification output layer can determine the corresponding petroleum type according to the processing result data; judging whether the output petroleum type is the same as the corresponding petroleum type label or not, if so, training next information sample data, and if not, adjusting the parameters of each information identification hidden layer to enable the output petroleum type to be the same as the corresponding petroleum type label; and (4) taking the information identification initial neural network after all information sample data are trained as an information identification neural network model.

In a specific embodiment, the apparatus further comprises: the oil order training module is specifically used for:

acquiring preset quantity of petroleum order sample data, and adding a corresponding petroleum type label for each petroleum order sample data, wherein the quantity of the petroleum type labels is one or more; the method comprises the steps of constructing an order identification initial neural network in advance, wherein the order identification initial neural network comprises the following steps: the system comprises an order identification input layer, M order identification hidden layers and an order identification output layer; inputting 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 all data content output after the previous order identification hidden layer is processed; the last order identification hidden layer outputs the processing result data to the order identification output layer so that the order identification output layer can determine the corresponding petroleum type according to the processing result data; judging whether the output petroleum type is the same as the corresponding petroleum type label, if so, training the sample data of the next petroleum order, if not, calculating an order loss function according to the output petroleum type and the corresponding petroleum type label, and adjusting the parameters of the hidden layer for order recognition according to the order loss function to ensure that the output petroleum type is the same as the corresponding petroleum type label; and taking the order recognition initial neural network after the petroleum order sample data is completely trained as an order recognition neural network model.

In a specific embodiment, the apparatus further comprises: the ordering module is specifically used for:

receiving user refueling ordering information sent by a client, wherein the refueling ordering information comprises a target petroleum commodity, position information of the client, a target gas station and a refueling time period; extracting the position information of the client in the information of ordering the user to refuel, searching the position information of the target gas station in a map, and calculating the time consumed by the client to reach the target gas station; if the current time plus the journey consumed time is less than or equal to the latest time point of 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, sending refueling order information of a user to a refueling station end of the target gas station for confirmation receiving, and simultaneously generating a confirmation receiving instruction to be sent to a client, otherwise, refusing to receive the refueling order information of the user, generating a refusing receiving instruction to be sent to the client; and if the current time plus the vehicle journey consumed time is larger than the latest time point of the refueling time period, refusing to receive refueling order information of the user, generating a re-confirmation refueling time period instruction and sending the re-confirmation refueling time period instruction to the client.

In a specific embodiment, the apparatus further comprises: the docking module is specifically configured to:

receiving a command of entering a gas station sent by a client to acquire the position information of the client; determining at least one gas station with the distance less 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 receiving the selected target entering gas station sent by the client, integrating the target entering gas station and the command of entering the gas station, and sending the integrated information to the corresponding gas station terminal of the target entering gas station so that the gas station terminal establishes entering connection with the client through the server.

Based on the above embodiments of the method shown in fig. 1 and the apparatus shown in fig. 2, in order to achieve the above object, an electronic device is further provided in the embodiments of the present application, 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, the memory 32 stores a computer program, and the processor 31 implements the server-side oil 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 (which may be a CD-ROM, a usb disk, a removable hard disk, or the like), and includes several instructions for enabling an electronic device (which may be a personal computer, a server, or a network device, or the like) to execute the method according to the 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, a WI-FI module, and so forth. The user interface may include a Display screen (Display), an input unit such as a keypad (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., a bluetooth interface, WI-FI interface), etc.

It will be understood by those skilled in the art that the structure of an electronic device provided in the present embodiment does not constitute a limitation of the physical device, and may include more or less components, or some components in combination, or a different arrangement of components.

Based on the embodiments of the method shown in fig. 1 and the apparatus shown in fig. 2, correspondingly, the present application also provides a storage medium, on which a computer program is stored, which when executed by a processor implements the server-side-based oil data processing method shown in fig. 1.

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

Through the above description of the embodiments, those skilled in the art will clearly understand that the present application can be implemented by software plus a necessary general hardware platform, and can also be implemented by hardware.

By applying the technical scheme, the pre-established information recognition neural network model can be used for determining the first to-be-pushed petroleum type to be recommended according to the vehicle owner information and the vehicle information sent by the client, and the pre-established order recognition neural network model is used for determining the second to-be-pushed petroleum type to be recommended according to the petroleum order data stored in the client, so that the server can combine the two to-be-pushed petroleum types to determine the target petroleum information matched with the user and the vehicle of the user, and the target petroleum information is sent to the client to be displayed in the information recommendation column corresponding to the display screen. Therefore, the server can automatically recommend the oil information for the user, and the recommended oil information is more in line with the actual requirements of the user or the vehicle of the user, so that convenience is provided for the user.

Those skilled in the art will appreciate that the figures are merely schematic representations of one preferred implementation scenario and that the blocks or flow diagrams in the figures are not necessarily required to practice the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario may be distributed in the devices in the implementation scenario according to the description of the implementation scenario, or may be located in one or more devices different from the present implementation scenario with corresponding changes. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.

The above application serial numbers are for description purposes only and do not represent the superiority or inferiority of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of the present application, but the present application is not limited thereto, and any variations that can be made by those skilled in the art are intended to fall within the scope of the present application.

Claims

1. A server-side-based petroleum data processing method is characterized by comprising the following steps:

2. The server-side based petroleum data processing method according to claim 1, further comprising:

3. The server-side-based oil data processing method according to claim 1, wherein the step of obtaining corresponding display information according to the received role authority information in the account login instruction sent by the client, and sending the display information to the corresponding client specifically comprises the steps of:

4. The server-side-based oil data processing method according to claim 1, wherein before the receiving client side sends owner information and/or vehicle information, a first petroleum type to be pushed is determined according to the owner information and/or the vehicle information by using a pre-constructed information recognition neural network model, and the method further comprises:

5. The server-side based oil data processing method according to claim 1, wherein before the receiving client sends oil order data and a second petroleum type to be pushed is determined according to the oil order data by using a pre-constructed order recognition neural network model, the method further comprises:

6. The server-side based petroleum data processing method according to claim 1, further comprising:

7. The server-side based petroleum data processing method according to claim 1, further comprising:

8. A server-based oil data processing device is characterized by comprising:

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the server-side petroleum data processing method according to any one of claims 1 to 7 when executing the computer program.

10. A storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of the server-side based oil data processing method according to any one of claims 1 to 7.