CN110796277B - Recommendation method, recommendation device and storage medium - Google Patents
Recommendation method, recommendation device and storage medium Download PDFInfo
- Publication number
- CN110796277B CN110796277B CN201910930660.2A CN201910930660A CN110796277B CN 110796277 B CN110796277 B CN 110796277B CN 201910930660 A CN201910930660 A CN 201910930660A CN 110796277 B CN110796277 B CN 110796277B
- Authority
- CN
- China
- Prior art keywords
- information
- fishing
- recommendation
- target
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/02—Reservations, e.g. for tickets, services or events
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0603—Catalogue ordering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Abstract
The embodiment of the invention discloses a recommendation method, a recommendation device and a storage medium; wherein the method comprises the following steps: receiving reservation information of a first user; the reservation information comprises a target requirement category and a target operation date; according to the target demand type, obtaining historical activity information of the first user related to the target demand type, and fishing boat operation information and environment information in a preset time period before a target operation date; and generating a recommendation list based on the historical activity information of the first user, and the fishing boat operation information and the environment information in a preset time period before the target operation date.
Description
Technical Field
The present invention relates to the field of data analysis and recommendation, and in particular, to a recommendation method, apparatus, and storage medium.
Background
Most of the current information recommendation methods recommend information to users through historical behaviors of the users (such as historical browsing data, historical operating data and historical search data). However, for the fishery industry, due to the particularity of the industry, information recommendation only according to the historical behaviors of the user cannot accurately provide fresh and interesting information for the user.
Disclosure of Invention
In view of this, embodiments of the present invention are expected to provide a recommendation method, apparatus, and storage medium, which can accurately provide fresh product information for a user in combination with industrial features of a fishing product to improve the satisfaction of the user.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
the embodiment of the invention provides a recommendation method, which comprises the following steps:
receiving reservation information of a first user; the reservation information comprises a target requirement category and a target operation date;
according to the target demand type, obtaining historical activity information of the first user related to the target demand type, and fishing boat operation information and environment information in a preset time period before a target operation date;
and generating a recommendation list based on the historical activity information of the first user, and the fishing boat operation information and the environment information in a preset time period before the target operation date.
In the above scheme, the obtaining fishing boat operation information within a preset time period before a target operation date according to the target demand type includes:
collecting first fishing boat operation information in a preset time period before a target operation date according to the target demand type; the first fishing boat operation information includes: information of operating fishing vessels, information of planning operation fishing vessels;
and correcting the collected first fishing boat operation information based on the weather information to obtain second fishing boat operation information.
In the above solution, the generating a recommendation list based on the historical activity information of the first user and the fishing boat operation information and environment information in a preset time period before the target operation date includes:
constructing a recommendation model based on the historical activity information, and obtaining a first recommendation list according to the recommendation model;
and correcting the first recommendation list based on the fishing boat operation information and the environment information in a preset time period before the target operation date to generate a second recommendation list.
In the above scheme, the recommendation list is displayed in an order according to one of unit parameters, total time for completing operations, total storage quantity, total preset quantity and historical operation frequency of the first user.
In the above solution, the recommendation list is displayed in order by unit parameters, and the method includes:
receiving a unit parameter interval selected by the first user;
and based on the selected unit parameter interval, sorting and displaying the unit parameters in the unit parameter interval according to the size of the unit parameters.
In the above scheme, the environment information includes: at least one of fishery news information and weather information.
An embodiment of the present invention further provides a recommendation apparatus, where the apparatus includes: the device comprises a receiving unit, an obtaining unit and a generating unit; wherein the content of the first and second substances,
the receiving unit is used for receiving reservation information of a first user; the reservation information comprises a target requirement category and a target operation date;
the acquisition unit is used for acquiring historical activity information of the first user related to the target demand type and fishing boat operation information and environment information in a preset time period before a target operation date according to the target demand type;
the generating unit is used for generating a recommendation list based on the historical activity information of the first user, and the fishing boat operation information and the environment information in a preset time period before the target operation date.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements any of the steps of the above-mentioned method.
An embodiment of the present invention further provides a recommendation apparatus, including: a processor and a memory for storing a computer program operable on the processor, wherein the processor is operable to perform any of the steps of the above method when executing the computer program.
The recommendation method, the recommendation device and the storage medium provided by the embodiment of the invention can acquire the information associated with the target demand type in the reservation information in the historical activity information of the first user based on the reservation information of the first user, acquire the fishing vessel operation information and the environment information in the preset time period before the target operation date in the reservation information, and generate the recommendation list through the 3 types of information. Therefore, the characteristics that the fishing product industry is easily influenced by the environment and the fishing boat operation condition can be combined, the fresh and interesting product information can be accurately provided for the user, and the user experience can be improved.
Drawings
Fig. 1 is a first schematic flow chart illustrating an implementation of a recommendation method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an implementation flow of a recommendation method according to an embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating an implementation process of a recommendation method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a recommendation device according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a specific hardware structure of a recommendation device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention.
All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to accurately provide fresh information interesting to a user, an embodiment of the present invention provides a recommendation method, as shown in fig. 1, the method includes:
It should be noted that the recommendation method may be applied to an information recommendation platform, where the information recommendation platform is used to recommend information for a user using the platform; the first user may be any user using the information recommendation platform. The information recommended by the information recommendation platform can be used for users to know products, and can also be used for providing an information collection channel for information sharing.
In the embodiment of the invention, the information recommendation platform can be specifically a fishing product recommendation platform and is used for recommending and sharing fishing product information.
It should be noted that the reservation information is used to represent operation information that the first user desires to perform on the information recommendation platform. The target requirement category is used for representing the category of operations which the first user desires to perform on the information recommendation platform, and the target requirement category can be the category of learning and introducing fishing products, the category of inquiring information of fishing products and the like. The target operation date is used for representing the date that the first user desires to operate on the information recommendation platform.
As a specific example, assuming that the A user desires to introduce a batch of fishing products in No. 8/month and No. 15, the information recommendation platform recommends fishing product information to the A user based on the reservation request of the A user; in this step, the reservation information is: 8, 15, introducing a batch of fishing products; the target demand categories are: recommending a fishing product; the target operation date is as follows: 8 month 15.
It should be further noted that the reservation information may further include: a target operating address; the target operation address is used for representing an address where the first user desires to operate on the information recommendation platform.
As a specific example, suppose A user desires 8 months 15 to introduce a batch of fishing products in Wenzhou, but specifically which fishing products A user may not be presently thinking. Therefore, according to the demand that the user A wants to introduce a batch of fishing products, the related information and the environmental information of the fishing boat which can be operated before 8 months and 15 th, and the historical information of the user A for introducing and searching the fishing products in the past can be obtained, and the information of the fishing products which can be provided by the user A and can be interested by the user A in the Wenzhou of 8 months and 15 th can be provided for the user A through the information.
It should be noted that, when the user explicitly knows which product the user wants to know and introduce, the reservation information may include a specific product name, and the operation information of the fishing vessel in a preset time period before the target operation date may be obtained according to the product name. Here, since the user has already clarified the demand, the influence of the historical activity information and the environmental information of the user is not large and may not be considered.
As a specific example, assume that the received subscription information of the a subscriber is: no. 8/15 wants to introduce abalone, so that the operation information of the fishing boat in a preset time period before No. 8/15 can be directly inquired to recommend abalone.
In practical applications, the reservation information may further include other contents, such as a target price interval, a target operation object, and the like; the target price interval is the price interval of the fishing products, and the target operation object is the merchant providing the fishing products.
102, acquiring historical activity information of the first user associated with the target demand type, and fishing boat operation information and environment information in a preset time period before a target operation date according to the target demand type.
Here, the historical activity information is used to characterize information corresponding to historical behaviors of the first user, and the historical activity information includes: at least one of historical operation records and historical search records.
It should be noted that the historical operation record is an operation record that the first user has completed; taking fishing products related operations as an example: and the historical operation record is the historical fishing product transaction order record.
The historical search record is a search record of the first user on the information recommendation platform recently; for example, the first user has searched for saury in the last week through the information recommendation platform, or has searched for keywords containing saury in other search engines under the browser.
The preset time period is a certain time period before the target operation date; by obtaining the information of the operation fishing boats in the preset time period before the target operation date, determining which fishing boats can be operated in the sea, and realizing that the fishing boats can provide fresh fishing products when the target operation date is reached.
It should be further noted that, the obtaining of the fishing boat operation information within the preset time period before the target operation date according to the target demand category includes: collecting first fishing boat operation information in a preset time period before a target operation date according to the target demand type; the first fishing boat operation information includes: information of operating fishing vessels, information of planning operation fishing vessels; and correcting the collected first fishing boat operation information based on the environment information to obtain second fishing boat operation information.
The information of the operating fishing boat and the information of the planning operation fishing boat can be obtained through the fishing boat information platform. Here, the fishing boat information platform may be a platform in which parameter specification information of the fishing boat, historical fishing records, and operation conditions of the fishing boat are recorded. The parameter specification information of the fishing boat comprises: ship number, scale, main fish catching, etc.; the historical fishing record comprises: fishing time, fishing location, fish product and yield, landing location, transaction price, etc.
Specifically, when the ship is used for capturing fishing products, the ship needs to be registered in relevant departments, specification parameters and the like of the ship are recorded, and the fishing boat information platform can call the parameters, collect the operation condition of the ship at any time and record the planned operation time of the ship.
As a specific example, assuming that the a user desires 8 th 15 th to introduce a batch of fishing products in wenzhou, the preset time period may be set to 8 th 5 to 8 th 10 considering the time of the sea work and the time required for the return to port. Thus, by acquiring information on fishing boats operating from 8 th 5 to 8 th 10 and/or information on fishing boats planned for operation, it is ensured that fresh fishing products can be provided to the user at 8 th 15.
It should be noted that the environmental information refers to public information that affects the actual operation condition of the fishing boat, and includes: at least one of fishery news information and weather information; other situations, such as policy restrictions, are of course also included.
The weather information refers to information related to weather, and includes: season information, climate information, weather information; the weather information may be obtained through a weather forecast website or a news channel.
Here, in a normal situation, the operation condition of the fishing boat is greatly influenced by seasons and weather, and weather information in a preset time period before a target operation date needs to be acquired, and the collected first fishing boat operation information is corrected based on the weather information to obtain second fishing boat operation information.
It should be noted that the operation condition of the fishing boat is sometimes influenced by fishery news information; therefore, fishery news information in a preset time period before the target operation date can be obtained; and determining the information of the operating fishing boat and the information of the planning operation fishing boat in a preset time period based on the fishery news information. Here, the fishery news information refers to relevant information of fishery in a certain sea area, for example, the overall predicted fishing amount, the large-area crude oil leakage condition, and the like; the fishery news information can be obtained by collecting news information released by some official websites.
Here, the correcting the collected first fishing boat work information based on the environmental information may include: performing grade evaluation on the acquired environmental information based on a preset rule to obtain an evaluation result; judging whether to correct the first fishing boat operation information or not based on the evaluation result; determining that the first fishing boat operation information needs to be corrected, and acquiring a correction factor, wherein the correction factor is used for representing the degree of correcting the first fishing boat operation information; and correcting the collected first fishing boat operation information based on the obtained correction factor.
It should be noted that the preset rule may be a calculation model, and the calculation model is pre-configured in the information recommendation platform to obtain the evaluation result corresponding to the environment information through the calculation model after the environment information is obtained.
The calculation model can be a calculation formula, the evaluation result can be a specific numerical value, and whether the first fishing boat operation information is corrected or not can be judged in a threshold value setting mode. Specifically, if the set evaluation result is larger than the threshold value, the first fishing boat operation information is considered to need to be corrected. For example, if the evaluation result is 6 and the threshold value is 3, it is determined that the first fishing vessel operation information needs to be corrected.
The setting of the correction factor may be to set a corresponding correction factor for each evaluation result as required, configure a mapping table about mapping relationships between a plurality of sets of evaluation results and corresponding correction factors in the information recommendation platform, and obtain the correction factor corresponding to each evaluation result by searching the mapping table. For example, the correction factor corresponding to the evaluation result of 6 is set to 0.6, the correction factor corresponding to the evaluation result of 1 is set to 0.1, the correction factor corresponding to the evaluation result of 8 is set to 0.8, and the larger the correction factor is, the greater the degree of correction of the first fishing boat operation information is required to be.
Based on the obtained correction factor, the collected first fishing boat operation information is corrected, and the number of fishing boats planned to be operated in the first fishing boat operation information can be obtained, and the correction factor is multiplied by the obtained number of fishing boats planned to obtain the number of fishing boats actually planned to be operated in the second fishing boat operation information. Here, since the fishing vessel being operated is already going out of the sea for operation, it is not considered here.
As an example, if the obtained evaluation result is 6, the correction factor is 0.6, and the first fishing boat operation information needs to be corrected, and if the number of fishing boats planned to be operated in the first fishing boat operation information is 10, the number of fishing boats actually planned to be operated in the second fishing boat operation information is 6. It should be noted that the correction method is also applicable to the correction of the recommendation list.
Therefore, the fishing boat operation condition in the preset time period before the target operation date is judged through the weather information and/or the fishery news information, and the actual prediction of the fishing boat operation condition can be realized. However, in practical applications, due to the fact that the weather conditions are variable, the weather factors have a greater influence on the operation of the fishing boat, and therefore the collected first fishing boat operation information can be corrected based on the weather factors only to obtain second fishing boat operation information.
As an example, assume that a user a desires No. 8/15 to introduce a batch of fishing products in wenzhou, and based on the demand, weather information and/or fishery news information within a preset time period before No. 8/15, such as No. 8/5 to No. 8/10, is acquired. If the weather information acquired from No. 8 month 5 to No. 8 month 10 is sunny and no crude oil leakage and other harmful conditions occur in the sea area near Wenzhou, the operation condition of the fishing vessel recorded by the fishing vessel information platform can be directly called. Assuming that the acquired weather information in 8 th 5 th to 8 th 10 th months is rainstorm and/or damage such as crude oil leakage in a nearby sea area, after the level corresponding to the environmental information is calculated, considering safety factors, the fishing boat which is planned to go out of the sea in 8 th 5 th to 8 th 10 th months may not go out of the sea for operation, and at the moment, the operation information of the fishing boat only comprises the information of the fishing boat which is in operation.
And 103, generating a recommendation list based on the historical activity information of the first user, the fishing boat operation information and the environment information in a preset time period before the target operation date.
It should be noted that the recommendation list includes at least one piece of product data; the product data includes: marine product name, specification, place of production, available quantity (KG or ton), available time period, estimated transaction price interval (yuan), transaction location, transportation cost estimation, etc.
As an example, the product data may be: abalone, twelve heads, Dalian, 8 tons, 2 weeks, 320 Yuan-800 Yuan, Dalian, 20 Yuan/km, etc.
In the information recommendation of fishing products, the historical activity information of the first user and the operation information of the fishing vessel in the preset time period before the target operation date have reference to the generation of the recommendation list. After the information meeting the requirements of the user is found, the information is displayed in a list form.
The recommendation list can be displayed in a sorting mode according to unit parameters, total time for completing operation, total storage quantity, total preset quantity and historical operation frequency of the first user.
In practical application, after determining (interesting) fresh fishing products meeting the user requirements by combining historical activity information of the user, operation information of the fishing boat in a preset time period before a target operation date and environment information, the determined fishing product information needs to be sequenced and displayed.
Here, the above-mentioned ranking display by the unit parameter means ranking display by the height of the unit parameter. Taking the related operations of the fishing products as an example, the marine products of the same type can be displayed in order of the price.
As a specific example, after it is determined that abalone is a product of interest to the user, if 3 shops are queried to sell abalone on the target operation date, abalone provided by the 3 shops are displayed in a sorted manner according to the price.
The step of carrying out sequencing display according to the total time consumption of the finished operation means that the total time consumption of the finished operation is guaranteed. Taking the related operations of the fishing products as an example, the display can be sorted according to the total consumption time from delivery to receiving.
The sorting by total storage quantity display is sorting by the size of the storage quantity. Taking the recommendation of fishing products as an example, 3000 fishing products in a certain fishing product and 2000 fishing products in another fishing product, sorting can be performed based on the size of the total inventory.
The sorting display in the total predetermined number refers to sorting in the size of the predetermined total number. Taking the relevant operations of the fishing products as an example, a fishing product is predetermined 3000 times and another fishing product is predetermined 2000 times, the sorting may be based on the predetermined total number of sizes.
The step of performing the sorting display according to the historical transaction frequency of the first user refers to performing the sorting display according to the historical operation frequency of the user on a certain product. Taking the related operations of the fishing products as an example, if a user of one fishing product A browses and deals 10 times in the past and another user of the fishing product A browses and deals 6 times in the past, the historical deal amount of the product can be sorted based on the user.
The recommendation list is displayed in an ordering mode according to unit parameters and comprises the following steps: receiving a unit parameter interval selected by the first user; and based on the selected unit parameter interval, performing sorting display in unit price in the unit parameter interval.
Here, after determining the (interesting) fresh fishing products meeting the user's needs, the unit parameters of the fishing products can be counted and sorted into a plurality of price intervals. For example, the unit parameter interval may be divided into 0-100, 100-150, 150-200, and the like.
Here, the characteristic parameters include the type, unit price, quantity, quality, etc. of the fishing product; the quality may be characterized by freshness, damage, etc.
It should be further noted that before the recommendation list is generated, a recommendation model needs to be constructed.
Here, the recommended model may be a long-short term memory (LSTM) model, a Back-ProPagation neural Network (BP) model, or other neural Network models. Among them, the LSTM model, which is a specific form of RNN (Recurrent neural network), can be used to process data with sequence (sequence) properties, such as time series data. Through the processing of the LSTM model, the preference of the user can be well predicted based on the historical data, and a preliminary recommendation list, namely the first recommendation list, is generated according to the preference of the user.
As an example, assuming that the A user desires to introduce a batch of fishing products in No. 8/month and No. 15, the historical operation records of the A user in 4-7 months, namely historical orders, historical search records and the like, can be obtained, and the historical operation records in 4-7 months are taken as training data. If 3 sets of training data are set: taking operation data of 4 months as input and operation data of 5 months as output; taking 5-month operation data as input and 6-month operation data as output; taking operation data of 6 months as input and operation data of 7 months as output; and extracting the characteristic parameters of the 3 groups of training data, and constructing a recommendation model based on the 3 groups of characteristic parameters. Thus, fishing products that may be of interest to the user in month 8 are predicted from the historical operating records of months 4-7.
In this way, the generating of the recommendation list based on the historical activity information of the first user and the operation information and the environment information of the fishing boat in the preset time period before the target operation date includes: constructing a recommendation model based on the historical activity information, and obtaining a first recommendation list according to the recommendation model; (ii) a And correcting the first recommendation list based on the fishing boat operation information and the environment information in a preset time period before the target operation date to generate a second recommendation list.
It should be noted that the first recommendation list is obtained through the historical operation records of the first user, and for the fishing products, since weather information and ship-to-sea conditions have great influence on the quantity and types of the fishing products, the first recommendation list generated based on historical data is not capable of meeting the actual needs of the user, and the first recommendation list needs to be corrected to generate a second recommendation list which is more in line with the needs (interests) of the user and has fresher products.
As described above, the correcting the first recommendation list based on the fishing vessel work information and the environmental information in the preset time period before the target operation date may include: grading the fishing boat operation information and the environment information in a preset time period before the obtained target operation date based on a preset rule to obtain a grading result; judging whether to modify the first recommendation list based on the evaluation result; determining that the first recommendation list needs to be corrected, and acquiring a correction factor, wherein the correction factor is used for representing the degree of correcting the first recommendation list; and modifying the first recommendation list based on the obtained modification factor.
Correspondingly, new fishing data can be predicted through the historical fishing boat fishing records. For example, by fishing boat fishing records in the last 8 months, the fish that may be fished in the 8 months of the year are predicted, as well as the quantity. Similarly, the fishing boat fishing record can be corrected through the environmental information to generate a new fishing record.
As an example, the fat head fish in the previous 6-8 months catches 10 tons; the obese fish in the last 6-8 months catches 8 tons, so that 8-10 tons of the obese fish can be probably caught in the current year. If the climate acquired in the 6-8 month year is abnormal, the acquired climate information influences the fishing amount, and the fishing amount of the fishing boat can be corrected through the environmental information to determine the new fishing amount.
According to the recommendation method provided by the embodiment of the invention, based on the received reservation information, the historical activity information of the first user corresponding to the reservation information is obtained, the operation information of the fishing vessel in the preset time period before the target operation date is obtained, and the recommendation list is generated according to the historical activity information and the fishing vessel operation condition. In this way, the working condition of the fishing boat can be determined through the target operation date to ensure the freshness of the recommended fishing products, and the recommendation of specific products is carried out based on the historical activity information, so that interesting and fresh fishing products are recommended for the user.
An embodiment of the present invention provides a recommendation method, and fig. 2 is a schematic diagram illustrating an implementation flow of the recommendation method provided in the embodiment of the present invention, as shown in fig. 2, the method mainly includes the following steps:
The reservation information includes a target demand type and a target operation date. The recommendation method can be applied to an information recommendation platform, and in the embodiment of the invention, the information recommendation platform can be a fishing product recommendation platform.
It should be further noted that the reservation information is used to characterize the operation information that the first user desires to perform on the information recommendation platform. The target requirement category is used for representing the category of operations which the first user desires to perform on the information recommendation platform, and the target requirement category can be the category of learning and introducing fishing products, the category of inquiring information of fishing products and the like. The target operation date is used for representing the date that the first user desires to operate on the information recommendation platform.
At step 202, historical activity information of a first user associated with a target demand category is obtained.
It should be noted that, according to the target demand category, the historical activity information of the first user associated with the target demand category may be determined. The historical activity information includes: at least one of historical operation records and historical search records.
It should be further noted that the historical operation record is an operation record that the first user has completed; taking the relevant operations of the fishing products as an example: and the historical operation record is the historical fishing product transaction order record. The historical search record is a search record of the first user on the information recommendation platform recently; for example, the first user has searched for saury in the last week through the information recommendation platform, or has searched for keywords containing saury in other search engines under the browser.
After obtaining the historical activity information of the first user, the process proceeds to step 205.
It should be noted that the preset time period is a certain time period before the target operation date; the environment information includes: fishery news information, weather information; the weather type information includes: season information, climate information, weather information. The weather information, the climate information and the season information can be acquired through a weather forecast website or a news channel.
And step 204, obtaining the fishing boat operation information in a preset time period before the target operation date.
It should be noted that by acquiring information of the operating fishing boats within a preset time period before the target operation date, which fishing boats are going to be operated in the sea is determined, so that the fishing boats in the sea operation can provide fresh fishing products when the target operation date is reached.
The information of the operating fishing boat and the information of the planning operation fishing boat can be obtained through a fishing boat information platform, and the fishing boat information platform records the parameter specification information, the historical fishing record and the operation condition of the fishing boat.
It should be noted that steps 202, 203, and 204 are not in obvious sequence.
The historical operation record of the first user is used as training data; and extracting the characteristic parameters of the training data, and constructing a recommendation model according to the characteristic parameters. The characteristic parameters include the type, unit price, quantity, quality and the like of the fishing products, and the quality can be characterized by freshness, damage degree and the like.
It should also be noted that the step 205 may be performed after the step 202 and before the step 203.
At step 206, a first recommendation list is generated.
It should be noted that the first recommendation list is obtained through the historical operation record of the first user.
It should be noted that, for fishing products, since weather information and ship-to-sea conditions have great influence on the number and types of the fishing products, a first recommendation list generated based on historical data only cannot meet the actual needs of a user, and needs to be modified to generate a second recommendation list which is more in line with the needs of the user (interesting) and has a fresher product, and specifically, the first recommendation list may be modified based on second fishing vessel operation information and environment information to generate the second recommendation list.
According to the embodiment of the invention, based on the received reservation information, the historical activity information of the first user corresponding to the reservation information is obtained, the operation information of the fishing boat in the preset time period before the target operation date is obtained, and the recommendation list is generated according to the historical activity information and the operation condition of the fishing boat. In this way, the working condition of the fishing boat can be determined through the target operation date to ensure the freshness of the recommended fishing products, and the recommendation of specific products is carried out based on the historical activity information, so that interesting and fresh fishing products are recommended for the user.
An embodiment of the present invention provides a recommendation method, and fig. 3 is a schematic flow chart illustrating an implementation process of the recommendation method provided in the embodiment of the present invention, as shown in fig. 3, the method mainly includes the following steps:
The reservation information includes a target demand type and a target operation date.
As a specific example, assuming that A user desires to introduce a batch of fishing products at 8 months and 15, based on the reservation request of A user, the information recommendation platform will recommend fishing product information to A user; in this step, the reservation information is: 8, 15, introducing a batch of fishing products; the target demand categories are: recommending a fishing product; the target operation date is as follows: 8 month 15.
It should be noted that the historical operation record is an operation record that the first user has completed; taking the relevant operations of the fishing products as an example: and the historical operation record is the historical fishing product transaction order record. The historical search record is a search record of the first user on the information recommendation platform recently; for example, the first user has searched for saury in the last week through the information recommendation platform, or has searched for keywords containing saury in other search engines under the browser.
It should be further noted that, after the obtaining of the historical activity information of the first user is completed, the step 306 is proceeded to.
It should be noted that the environment information includes: fishery news information, weather information; the weather type information includes: season information, climate information, weather information. The weather information, the climate information and the season information can be acquired through a weather forecast website or a news channel.
It should be noted that the environmental information may be used to correct the fishing boat operation information. By acquiring the environmental information in the preset time period before the target operation date, the fishing boat operation condition in the preset time period before the target operation date can be judged, so that the actual prediction of the fishing boat operation condition is realized.
After the acquisition of the environment information is completed, the process proceeds to step 305.
And step 304, acquiring first fishing boat operation information in a preset time period before the target operation date.
It should be noted that the first fishing boat operation information can be obtained through a fishing boat information platform, and the fishing boat information platform records parameter specification information, historical fishing records and operation conditions of the fishing boat. Specifically, when the ship is used for capturing fishing products, the ship needs to be registered in relevant departments, specification parameters and the like of the ship are recorded, the fishing boat information platform calls the parameters, the operation condition of the ship is collected at any time, and the planned operation time of the ship is recorded.
It should be noted that steps 302, 303, and 304 are not in obvious sequence.
And 305, obtaining second fishing boat operation information.
It should be noted that, the actual operation condition of the fishing boat is greatly influenced by seasons and weather, and sometimes also influenced by fishery news information; in this way, the environmental information in the preset time period before the target operation date can be acquired, and the information of the operating fishing boat and the information of the planning fishing boat, namely the second fishing boat operation information in the preset time period can be determined.
After the second fishing boat operation information is obtained, the process proceeds to step 308.
It should be noted that the recommendation model may be constructed based on the historical operation records of the first user. Specifically, taking the historical operation record of the first user as training data; and extracting the characteristic parameters of the training data, and constructing a recommendation model according to the characteristic parameters. The characteristic parameters include the type, unit price, quantity, quality and the like of the fishing products, and the quality can be characterized by freshness, damage degree and the like.
It should be noted that the first recommendation list is obtained through the historical operation record of the first user.
It should be noted that, for fishing products, since weather information and ship-to-sea conditions have great influence on the number and types of the fishing products, a first recommendation list generated based on historical data only cannot meet the actual needs of a user, and needs to be modified to generate a second recommendation list which is more in line with the needs of the user (interesting) and has a fresher product, and specifically, the first recommendation list may be modified based on second fishing vessel operation information and environment information to generate the second recommendation list.
According to the recommendation method provided by the embodiment of the invention, based on the received reservation information, the historical activity information of the first user corresponding to the reservation information and the operation information of the fishing vessel in the preset time period before the target operation date are obtained, a first recommendation list is generated according to the historical activity information and the fishing vessel operation condition, and the first recommendation list is corrected according to the operation information and the environment information of the fishing vessel to generate a second recommendation list. Therefore, the operation condition of the fishing boat can be determined through the target operation date to ensure the freshness of the recommended fishing products, and the specific products are recommended based on the historical activity information, the operation information of the fishing boat and the environment information, so that the interested and fresh fishing products are recommended for the user.
Based on the same inventive concept of the above embodiments, an embodiment of the present invention provides a recommendation apparatus, fig. 4 is a schematic structural diagram of a recommendation apparatus 400 provided in an embodiment of the present invention, as shown in fig. 4, a receiving unit 401, an obtaining unit 402, and a generating unit 403; wherein the content of the first and second substances,
the receiving unit 401 is configured to receive reservation information of a first user; the reservation information comprises a target requirement category and a target operation date;
the obtaining unit 402 is configured to obtain, according to the target demand category, historical activity information of the first user associated with the target demand category, and fishing boat operation information and environment information within a preset time period before a target operation date;
the generating unit 403 is configured to generate a recommendation list based on the historical activity information of the first user, and the fishing boat operation information and the environment information in a preset time period before the target operation date.
Note that, the acquiring unit 402 includes: a first acquisition unit 4021, a second acquisition unit 4022, and a third acquisition unit 4023;
the first obtaining unit 4021 is configured to obtain, according to the target demand category, historical activity information of the first user associated with the target demand category;
the second obtaining unit 4022 is configured to obtain information about the operation of the fishing vessel within a preset time period before a target operation date according to the target demand type;
a third obtaining unit 4023, configured to obtain, according to the target demand type, environmental information in a preset time period before a target operation date.
It should be noted that the second obtaining unit 4022 is specifically configured to collect, according to the target demand type, first fishing vessel operation information within a preset time period before a target operation date; the first fishing boat operation information includes: information of operating fishing vessels, information of planning operation fishing vessels; and correcting the collected first fishing boat operation information based on the environment information to obtain second fishing boat operation information.
The recommendation apparatus 400 further includes: a modeling unit 404;
the modeling unit 404 is configured to construct a recommendation model based on the historical activity information.
It should be further noted that the generating unit 403 includes: a first generation unit 4031 and a second generation unit 4032; the first generating unit 4031 is configured to obtain a first recommendation list according to the recommendation model;
the second generating unit 4032 is configured to modify the first recommendation list based on the fishing boat operation information and the environment information in a preset time period before the target operation date, and generate a second recommendation list.
It should be noted that the environment information includes: at least one of fishery news information and weather information.
It should be noted that the recommendation list is displayed in an order according to one of the unit parameter, the total time of completing the operation, the total storage quantity, the total preset quantity, and the historical operation frequency of the first user.
The recommendation list is displayed in an ordering mode according to unit parameters and comprises the following steps: receiving a unit parameter interval selected by the first user; and based on the selected unit parameter interval, sorting and displaying the unit parameters in the unit parameter interval according to the size of the unit parameters.
It should be noted that, because the principle of solving the problem of the recommendation apparatus 400 is similar to that of the aforementioned recommendation method, the specific implementation process and implementation principle of the recommendation apparatus 400 can be referred to the aforementioned method and implementation process, and repeated details are not repeated.
The recommending device provided by the embodiment of the invention acquires the historical activity information of the first user corresponding to the reservation information and the operation information of the fishing vessel in the preset time period before the target operation date based on the received reservation information, and generates the recommending list according to the historical activity information and the fishing vessel operation condition. In this way, the working condition of the fishing boat can be determined through the target operation date to ensure the freshness of the recommended fishing products, and the recommendation of specific products is carried out based on the historical activity information, so that interesting and fresh fishing products are recommended for the user.
It should be noted that, in the embodiments of the present invention, each component may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware or a form of a software functional module.
Based on the understanding that the technical solution of the embodiments of the present invention essentially or a part of the technical solution contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, and include several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Accordingly, embodiments of the present invention provide a computer storage medium storing a computer program that, when executed by at least one processor, performs the steps of the above-described embodiments.
Referring to fig. 5, a specific hardware structure of a recommendation apparatus 500 according to an embodiment of the present invention is shown, including: a network interface 501, a memory 502, and a processor 503; the various components are coupled together by a bus system 504. It is understood that the bus system 504 is used to enable communications among the components. The bus system 504 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 504 in fig. 5.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
The methods disclosed in the several method embodiments provided in the present application may be combined arbitrarily without conflict to obtain new method embodiments.
Features disclosed in several of the product embodiments provided in the present application may be combined in any combination to yield new product embodiments without conflict.
The features disclosed in the several method or apparatus embodiments provided in the present application may be combined arbitrarily, without conflict, to arrive at new method embodiments or apparatus embodiments.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (8)
1. A recommendation method, characterized in that the method comprises:
receiving reservation information of a first user; the reservation information comprises a target requirement category and a target operation date;
according to the target demand type, obtaining historical activity information of the first user related to the target demand type, and fishing boat operation information and environment information in a preset time period before a target operation date; wherein the historical activity information at least comprises: historical operation records and historical search records;
constructing a recommendation model based on the historical activity information, and obtaining a first recommendation list according to the recommendation model;
grading the obtained fishing boat operation information and environment information in a preset time period before the target operation date based on a preset rule to obtain a grading result;
judging whether to modify the first recommendation list based on the evaluation result;
acquiring a correction factor under the condition that the first recommendation list needs to be corrected based on the evaluation result; wherein the correction factor is used for characterizing the degree of correcting the first recommendation list;
and modifying the first recommendation list based on the modification factor to generate a second recommendation list.
2. The method according to claim 1, wherein the obtaining fishing boat operation information within a preset time period before a target operation date according to the target demand category comprises:
collecting first fishing boat operation information in a preset time period before a target operation date according to the target demand type; the first fishing boat operation information includes: information of operating fishing vessels, information of planning operation fishing vessels;
and correcting the collected first fishing boat operation information based on the environment information to obtain second fishing boat operation information.
3. The method of claim 1, wherein the recommendation list is displayed in an order of one of a unit parameter, a total time to complete an operation, a total number of stores, a total number of predetermined numbers, and a historical frequency of operations by the first user.
4. The method of claim 3, wherein the recommendation list is displayed in an order of unit parameters, comprising:
receiving a unit parameter interval selected by the first user;
and based on the selected unit parameter interval, sorting and displaying the unit parameters in the unit parameter interval according to the size of the unit parameters.
5. The method of claim 1, wherein the context information comprises: at least one of fishery news information and weather information.
6. A recommendation device, characterized in that the device comprises: the device comprises a receiving unit, an obtaining unit and a generating unit; wherein the content of the first and second substances,
the receiving unit is used for receiving reservation information of a first user; the reservation information comprises a target requirement category and a target operation date;
the acquisition unit is used for acquiring historical activity information of the first user related to the target demand type and fishing boat operation information and environment information in a preset time period before a target operation date according to the target demand type; wherein the historical activity information at least comprises: historical operation records and historical search records;
the generating unit is used for constructing a recommendation model based on the historical activity information and obtaining a first recommendation list according to the recommendation model; grading the obtained fishing boat operation information and environment information in a preset time period before the target operation date based on a preset rule to obtain a grading result; judging whether to modify the first recommendation list based on the evaluation result; acquiring a correction factor under the condition that the first recommendation list needs to be corrected based on the evaluation result; wherein the correction factor is used for characterizing the degree of correcting the first recommendation list; and modifying the first recommendation list based on the modification factor to generate a second recommendation list.
7. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
8. A recommendation device, comprising: a processor and a memory for storing a computer program operable on the processor, wherein the processor is operable to perform the steps of the method of any of claims 1 to 5 when the computer program is run.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910930660.2A CN110796277B (en) | 2019-09-29 | 2019-09-29 | Recommendation method, recommendation device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910930660.2A CN110796277B (en) | 2019-09-29 | 2019-09-29 | Recommendation method, recommendation device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110796277A CN110796277A (en) | 2020-02-14 |
| CN110796277B true CN110796277B (en) | 2022-01-28 |
Family
ID=69438797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910930660.2A Active CN110796277B (en) | 2019-09-29 | 2019-09-29 | Recommendation method, recommendation device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110796277B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111931038A (en) * | 2020-06-18 | 2020-11-13 | 珠海格力电器股份有限公司 | Method, device, equipment and storage medium for determining recommended starting time |
| CN112926930A (en) * | 2021-04-14 | 2021-06-08 | 广州市钛菱云科技有限公司 | Takeaway fresh-keeping method, system, equipment and computer readable storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7853473B2 (en) * | 2004-08-31 | 2010-12-14 | Revionics, Inc. | Market-based price optimization system |
| CN105760943A (en) * | 2016-02-29 | 2016-07-13 | 苏州上川智能科技有限公司 | Fresh product recommendation system |
| CN107944590B (en) * | 2016-10-13 | 2022-02-22 | 阿里巴巴集团控股有限公司 | Method and equipment for analyzing and forecasting fishing situations |
| CN106991601B (en) * | 2017-05-18 | 2021-02-26 | 广州市拓狗信息科技有限公司 | Aquatic product pushing method and system based on culture data |
| CN108876161A (en) * | 2018-06-26 | 2018-11-23 | 广东海洋大学 | A kind of appraisal procedure of fishing boat fishing capacity and technical benefits index |
-
2019
- 2019-09-29 CN CN201910930660.2A patent/CN110796277B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110796277A (en) | 2020-02-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180047071A1 (en) | System and methods for aggregating past and predicting future product ratings | |
| US20230306449A1 (en) | Pre-processing financial market data prior to machine learning training | |
| CN110796277B (en) | Recommendation method, recommendation device and storage medium | |
| CN109189990A (en) | A kind of generation method of search term, device and electronic equipment | |
| CN110647696B (en) | Business object sorting method and device | |
| CN108345601A (en) | Search result ordering method and device | |
| CN110580278A (en) | personalized search method, system, equipment and storage medium according to user portrait | |
| CN109242654A (en) | A kind of item recommendation method and system | |
| CN110991189A (en) | Method and system for generating decision result according to data acquired by acquisition module | |
| CN111124676A (en) | Resource allocation method and device, readable storage medium and electronic equipment | |
| CN112241495A (en) | Page updating method | |
| CN110825974B (en) | Recommendation system content ordering method and device | |
| CN111651669A (en) | Information recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN110555752A (en) | Personalized recommendation method and device, electronic equipment and readable storage medium | |
| CN110851708A (en) | Negative sample extraction method and device, computer equipment and storage medium | |
| CN108009727B (en) | Object evaluation method combining user comments | |
| WO2019200296A1 (en) | Computing systems and methods for improving content quality for internet webpages | |
| CN105243135A (en) | Method and apparatus for showing search result | |
| CN111046285B (en) | Recommendation ordering determining method, device, server and storage medium | |
| CN115187330A (en) | Product recommendation method, device, equipment and medium based on user label | |
| CN111639274B (en) | Online commodity intelligent sorting method, device, computer equipment and storage medium | |
| CN110418171B (en) | Media resource pushing method and device, storage medium and electronic device | |
| CN111127059B (en) | User quality analysis method and device | |
| CN113781134A (en) | Item recommendation method and device and computer-readable storage medium | |
| CN112487277A (en) | Data distribution method and device, readable storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 315000 No.98, Huiming Road, economic development zone, Fenghua District, Ningbo City, Zhejiang Province Patentee after: Ningbo haihaixian Information Technology Co.,Ltd. Address before: 315000 No.98, Huiming Road, economic development zone, Fenghua District, Ningbo City, Zhejiang Province Patentee before: NINGBO HAISHANGXIAN INFORMATION TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |