阅读说明：本技术 一种农产品全自动化管理方法、系统及存储介质 (Full-automatic management method and system for agricultural products and storage medium ) 是由 孙彤 黄贵恒 于 2021-06-24 设计创作，主要内容包括：本说明书实施例提供了一种农产品全自动化管理方法、系统和存储介质。所述农产品全自动化管理方法包括：基于与农产品相关的第一特征组,确定农产品的第一预测值,其中,第一预测值为农产品预设时间的价格；基于与农产品相关的第二特征组,确定农产品预设时间的宣传内容。(The embodiment of the specification provides a method, a system and a storage medium for fully automatically managing agricultural products. The full-automatic agricultural product management method comprises the following steps: determining a first predicted value of the agricultural product based on a first feature group related to the agricultural product, wherein the first predicted value is the price of the agricultural product at a preset time; and determining the propaganda content of the agricultural product at the preset time based on the second characteristic group related to the agricultural product.)

1. A method for fully automatically managing agricultural products comprises the following steps:

determining a first predicted value of the agricultural product based on a first feature group related to the agricultural product, wherein the first predicted value is a price of the agricultural product for a preset time;

and determining the promotional content of the agricultural product at the preset time based on a second characteristic group related to the agricultural product.

2. The method of claim 1, the determining a first predictive value for the agricultural product based on a first set of features associated with the agricultural product, comprising:

determining the first predictive value through a first model based on the first feature set, wherein the first feature set comprises at least one of a second predictive value of the agricultural commodity, a quality parameter of the agricultural commodity and a current price of the agricultural commodity, and the second predictive value is a damage rate of the agricultural commodity.

3. The method of claim 2, further comprising, prior to said determining a first predictive value for the agricultural product based on a first set of characteristics associated with the agricultural product:

obtaining the second predicted value through a second model based on a third feature set associated with the agricultural product, wherein the third feature set includes at least one of growth data of the agricultural product and environmental data of the agricultural product.

4. The method of claim 1, wherein determining promotional content for the agricultural commodity for a predetermined time based on a second set of characteristics associated with the agricultural commodity comprises:

determining a promotion strategy of the agricultural product preset time through a third model based on the second feature set, wherein the second feature set comprises at least one of the first predicted value, the state of the agricultural product preset time and growth data of the agricultural product;

and generating corresponding propaganda contents through a preset propaganda template based on the propaganda strategy.

5. A system for fully automatically managing agricultural products comprises:

the agricultural product prediction method comprises a first prediction value determination module, a first prediction value determination module and a second prediction value determination module, wherein the first prediction value determination module is used for determining a first prediction value of an agricultural product based on a first feature group related to the agricultural product, and the first prediction value is the price of a preset time of the agricultural product;

and the propaganda content determining module is used for determining propaganda content of the agricultural product at a preset time based on a second characteristic group related to the agricultural product.

6. The system of claim 5, the first predictor determination module to:

determining the first predictive value through a first model based on the first feature set, wherein the first feature set comprises at least one of a second predictive value of the agricultural commodity, a quality parameter of the agricultural commodity and a current price of the agricultural commodity, and the second predictive value is a damage rate of the agricultural commodity.

7. The system of claim 6, the first predictor determination module further comprising:

a second predicted value obtaining unit configured to obtain the second predicted value through a second model based on a third feature set related to the agricultural product, wherein the third feature set includes at least one of growth data of the agricultural product and environment data of the agricultural product.

8. The system of claim 5, the promotional content determination module to:

determining a promotion strategy of the agricultural product preset time through a third model based on the second feature set, wherein the second feature set comprises at least one of the first predicted value, the state of the agricultural product preset time and growth data of the agricultural product;

and generating corresponding propaganda contents through a preset propaganda template based on the propaganda strategy.

9. An apparatus for fully automatically managing agricultural products, comprising a processor for executing the method for fully automatically managing agricultural products according to any one of claims 1 to 4.

10. A computer-readable storage medium storing computer instructions, wherein when the computer instructions in the storage medium are read by a computer, the computer executes the method for full automation management of agricultural products according to any one of claims 1 to 4.

Technical Field

The specification relates to the field of computers, in particular to a method, a system and a storage medium for full-automatic management of agricultural products.

Background

In the process of selling agricultural products, some strategies for selling the agricultural products, including prices, propaganda strategies and the like, need to be determined according to actual conditions or states of the quality and the like of the agricultural products, so that the selling mode and the propaganda contents of the agricultural products are matched with the actual conditions, the condition that a user considers that the actual conditions are inconsistent with the propaganda is reduced, and the purchasing experience of the user is improved.

Therefore, there is a need for a method and system that can formulate a pre-set time marketing strategy based on the current condition of the agricultural product.

Disclosure of Invention

One aspect of the present description provides a method for fully automated management of agricultural products. The method comprises the following steps; determining a first predicted value of the agricultural product based on a first feature group related to the agricultural product, wherein the first predicted value is a price of the agricultural product for a preset time; and determining the promotional content of the agricultural product at the preset time based on a second characteristic group related to the agricultural product.

Another aspect of the present description provides a system for fully automated management of agricultural products. The system comprises: the agricultural product prediction method comprises a first prediction value determination module, a first prediction value determination module and a second prediction value determination module, wherein the first prediction value determination module is used for determining a first prediction value of an agricultural product based on a first feature group related to the agricultural product, and the first prediction value is the price of a preset time of the agricultural product; and the propaganda content determining module is used for determining propaganda content of the agricultural product at a preset time based on a second characteristic group related to the agricultural product.

Another aspect of the present specification provides an apparatus for fully automatically managing agricultural products, comprising a processor for performing a method for fully automatically managing agricultural products according to any one of claims 1 to 4.

Another aspect of the present specification provides a computer-readable storage medium storing computer instructions, wherein when the computer instructions in the storage medium are read by a computer, the computer executes the method for full-automatic agricultural product management.

Drawings

The present description will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:

FIG. 1 is a schematic diagram of an application scenario of a system for full automation management of agricultural products according to some embodiments of the present description;

FIG. 2 is a functional block diagram of a system for full automation management of agricultural products, according to some embodiments of the present description;

FIG. 3 is an exemplary flow diagram of a method for full automation management of agricultural products, according to some embodiments described herein;

FIG. 4 is an exemplary flow chart of a method of determining a first predictive value of an agricultural product according to some embodiments herein;

FIG. 5 is an exemplary flow diagram of a method for determining promotional content for a preset time of an agricultural product according to some embodiments of the present description;

FIG. 6 is a block diagram of a model for a system for automated management according to some embodiments of the present description.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "apparatus", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or operations may be removed from the processes.

The embodiment of the specification relates to a method, a system and a storage medium for fully automatically managing agricultural products. The full-automatic management method, system and storage medium for agricultural products can be applied to agricultural production, agricultural research, agricultural product storage and transaction. In some embodiments, the method, the system and the storage medium for fully automated management of agricultural products can be applied to management ends of internet of things of agricultural products, such as warehouses, agricultural greenhouses, supermarkets, shops, farmer markets and the like. In some embodiments, the agricultural product full-automatic management method, system and storage medium can be applied to an agricultural product purchasing end, such as a user terminal and the like. In some embodiments, the method, the system and the storage medium for fully automatically managing the agricultural products can be applied to other fields, such as environmental protection field and animal and plant rescue field. The full-automatic agricultural product management method, system and storage medium can provide services such as environmental monitoring, environmental prediction, animal and plant nursing and the like.

Fig. 1 is a schematic diagram of an application scenario of a system for fully automatically managing agricultural products according to some embodiments of the present disclosure.

The fully automated agricultural product management system 100 can acquire characteristics related to agricultural products and determine the damage rate of the agricultural products, the prices of the agricultural products at preset time and the propaganda contents at the preset time based on the model. The agricultural product related characteristic may be: quality parameters of the agricultural product, growth data of the agricultural product, current price of the agricultural product, and the like.

As shown in FIG. 1, the agricultural product full automation management system 100 may include a server 110, a processing device 120, a storage device 130, a first user terminal 140, a network 150, and a second user terminal 160.

In some embodiments, the server 110 may be configured to process information and/or data related to the agricultural automation management system 100, for example, may be configured to determine a first predictive value for an agricultural commodity based on a first set of characteristics related to the agricultural commodity. In some embodiments, the server 110 may be a single server or a group of servers. The server groups may be centralized or distributed, for example, the servers 110 may be distributed systems. In some embodiments, the server 110 may be local or remote. For example, server 110 may access information and/or data stored in storage device 130, first user terminal 140, second user terminal 150 via network 150. As another example, server 110 may be directly connected to storage device 130, first user terminal 140, and/or second user terminal 160 to access stored information and/or data. In some embodiments, the server 110 may be implemented on a cloud platform or provided in a virtual manner. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-tiered cloud, and the like, or any combination thereof.

In some embodiments, the server 110 may include a processing device 120. The processing device 120 may process information and/or data related to the agricultural automation management system 100 to perform one or more of the functions described herein. For example, the processing device 120 may determine a first predictive value for the agricultural product based on a first set of characteristics associated with the agricultural product, or determine promotional content for a preset time of the agricultural product based on a second set of characteristics associated with the agricultural product. In some embodiments, processing device 120 may include one or more processing engines (e.g., a single chip processing engine or a multi-chip processing engine). By way of example only, the processing device 120 may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an application specific instruction set processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.

Storage device 130 may be used to store data and/or instructions related to the full automation management of agricultural products. In some embodiments, storage device 130 may store data obtained/obtained from first user terminal 140 and/or second user terminal 160. In some embodiments, storage device 130 may store data and/or instructions that server 110 uses to perform or use to perform the exemplary methods described in this specification. In some embodiments, storage 130 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), and the like, or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state disks, and the like. Exemplary removable memory may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tape, and the like. Exemplary volatile read and write memories can include Random Access Memory (RAM). Exemplary RAM may include Dynamic Random Access Memory (DRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), Static Random Access Memory (SRAM), thyristor random access memory (T-RAM), and zero capacitance random access memory (Z-RAM), among others. Exemplary read-only memories may include model read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), digital versatile disc read-only memory, and the like.

In some embodiments, storage device 130 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-tiered cloud, and the like, or any combination thereof. In some embodiments, the storage device 130 may be connected to the network 150 to communicate with one or more components of the agricultural automation management system 100 (e.g., the server 110, the first user terminal 140, the second user terminal 160). One or more components of the agricultural automation management system 100 may access data or instructions stored in the storage device 130 via the network 150. In some embodiments, the storage device 130 may be directly connected to or in communication with one or more components of the agricultural automation management system 100 (e.g., the server 110, the first user terminal 140, the second user terminal 160). In some embodiments, storage device 130 may be part of server 110. In some embodiments, storage device 130 may be a separate memory.

The first user terminal 140 may be a requester for obtaining a first characteristic of an agricultural product and a second characteristic of the agricultural product. In some embodiments, the first user terminal 140 may be an individual, tool, or other entity directly related to obtaining the first characteristic of the agricultural product, the second characteristic of the agricultural product. In this specification, "user" and "user terminal" may be used interchangeably. In some embodiments, the first user terminal 140 may include a mobile device 140-1, a tablet 140-2, a laptop 140-3, a notebook 140-4, a camera 140-5, and the like, or any combination thereof. In some embodiments, camera 140-5 may include a combination of one or more of a 2D camera, a 3D camera, an infrared camera, and the like. The camera 140-5 may be used to acquire two-dimensional or three-dimensional image data of agricultural products. In some embodiments, the camera 140-5 may be a standalone camera or may be part of other devices, such as a cell phone camera, a computer camera, a vehicle camera, a drone camera, and the like. In some embodiments, camera 140-5 may be fixed or may be movable. In some embodiments, first user terminal 140 may include various sensors, such as, for example, a temperature sensor, a humidity sensor, various gas concentration sensors, an image sensor, etc., for collecting agricultural product-related data, such as, for example, growth data of the agricultural product, appearance data of the agricultural product, growth of the agricultural product, and stored environmental data, etc.

The network 150 may facilitate the exchange of information and/or data. In some embodiments, one or more components of the agricultural automation management system 100, e.g., the server 110, the first user terminal 140, the second user terminal 160, may send information and/or data to other components of the agricultural automation management system 100 via the network 150. For example, server 110 may obtain a first set of characteristics or a second set of characteristics of an agricultural commodity from first user terminal 140 via network 150. In some embodiments, the network 150 may be a wired network or a wireless network, or the like, or any combination thereof. By way of example only, network 150 may include a cable network, a wireline network, a fiber optic network, a telecommunications network, an intranet, the Internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a Bluetooth network, a ZigBee network, a Near Field Communication (NFC) network, a Global System for Mobile communications (GSM) network, a Code Division Multiple Access (CDMA) network, a Time Division Multiple Access (TDMA) network, a General Packet Radio Service (GPRS) network, an enhanced data rates for GSM evolution (EDGE) network, a Wideband Code Division Multiple Access (WCDMA) network, a High Speed Downlink Packet Access (HSDPA) network, a Long Term Evolution (LTE) network, a User Datagram Protocol (UDP) network, a Transmission control protocol/Internet protocol (TCP/IP) network, a Short Message Service (SMS) network, a network such as a network, a, A Wireless Application Protocol (WAP) network, an ultra-wideband (UWB) network, infrared, and the like, or any combination thereof. In some embodiments, the agricultural automation management system 100 may include one or more network access points. For example, a base station and/or wireless access point 150-1, 150-2, …, one or more components of the agricultural automation management system 100 may connect to the network 150 to exchange data and/or information.

The second user terminal 160 may be used to output and/or present information related to the agricultural product, for example, a promotion policy and/or promotion content of the agricultural product. In some embodiments, the second user terminal 160 may output various information generated by the server 110, such as promotional content of agricultural products, or directly present to a sales object of agricultural products. In some embodiments, second user terminal 160 may retrieve information from storage device 130 that needs to be output or presented in some embodiments. In some embodiments, the second user terminal 160 may be a similar or the same device as the first user terminal 140. In some embodiments, the second user terminal 160 may include a mobile device 160-1, a tablet 160-2, a laptop 160-3, a notebook 160-4, the like, any combination thereof, the like, or any combination thereof.

It should be noted that the agricultural product full automation management system 100 is provided for illustrative purposes only and is not intended to limit the scope of the present application. It will be apparent to those skilled in the art that various modifications and variations can be made in light of the description herein. For example, the agricultural automation management system 100 may also include an information source. As another example, the agricultural product full automation management system 100 may implement similar or different functions on other devices. However, such changes and modifications do not depart from the scope of the present application.

FIG. 2 is a functional block diagram of a system for full automation management of agricultural products, according to some embodiments of the present description. System 200 may be executed by processing device 120.

As shown in fig. 2, the processing device 120 may include a first predictive value determination module 210, a promotional content determination module 220.

The first predictive value determination module 210 may be configured to determine a first predictive value for the agricultural commodity based on a first set of characteristics associated with the agricultural commodity, wherein the first predictive value is a price of the agricultural commodity for a predetermined time.

In some embodiments, the first predicted value determining module 210 may predict and determine data related to the agricultural product, for example, a price of the agricultural product for a preset time, etc., through various means such as a model or an algorithm, based on other characteristics related to the agricultural product.

In some embodiments, first predictive value determination module 210 may determine the first predictive value through a first model based on the first set of characteristics, wherein the first set of characteristics includes at least one of a second predictive value of the agricultural commodity, a quality parameter of the agricultural commodity, and a current price of the agricultural commodity, and the second predictive value is a rate of damage to the agricultural commodity.

In some embodiments, the first predictive value determination module 210 may determine other content through the first model based on the first set of features. For example, the freshness cycle of the agricultural product, the expected sales of the agricultural product, etc. In some embodiments, the first predictive value determination module 210 may determine the first predictive value based on other content. For example, the first predictive value is determined based on a reference price given by a merchant, the first predictive value is determined based on a sales volume, and the like.

In some embodiments, the first predictor determination module 210 may include a second predictor obtaining unit 221.

In some embodiments, the second predicted value obtaining unit 221 may be configured to obtain the second predicted value through a second model based on a third feature set associated with the agricultural product, wherein the third feature set includes at least one of growth data of the agricultural product and environmental data of the agricultural product.

The promotional content determination module 220 may be used to determine promotional content.

In some embodiments, the promotion content determination module 220 may determine information related to a promotion of sale of an agricultural product by various means such as models or algorithms based on characteristics related to the agricultural product, such as promotion policies for a preset time of the agricultural product, promotion content, and the like.

In some embodiments, the promotion content determination module 220 may be configured to determine a promotion policy for the agricultural commodity preset time through a third model based on the second feature set, wherein the second feature set includes at least one of the first predicted value, a state of the agricultural commodity preset time, and growth data of the agricultural commodity; and generating corresponding propaganda contents through a preset propaganda template based on the propaganda strategy.

In some embodiments, the promotional content determination module 220 may determine other content via a third model based on the second set of characteristics. For example, predicted sales of agricultural products, discounted information on agricultural products, etc.

In some embodiments, the promotional content determination module 220 may determine promotional content based on other content. For example, promotional content is determined based on agricultural product forecasted sales, promotional content is determined based on network information, and the like.

FIG. 3 is an exemplary flow diagram of a method for full automation management of agricultural products, shown in accordance with some embodiments of the present description. The process 300 may be performed by the agricultural product full automation management system 100. For example, the process 300 may be performed by the processing device 120 described in fig. 1.

Step S302, a first predicted value of the agricultural product is determined based on a first feature set related to the agricultural product. And the first predicted value is the price of the preset time of the agricultural product. In some embodiments, this step S302 may be performed by the first predictor determining module 210.

The first feature set is one or more sets of data related to pricing of the agricultural product, such as a current price of the agricultural product, a quality of the agricultural product, a sales forecast for the agricultural product, and the like. In some embodiments, the first set of characteristics may include a rate of deterioration of the agricultural product, a quality parameter of the agricultural product, a current price of the agricultural product, and the like. In some embodiments, the data in the first set of characteristics may be predicted, for example, the rate of damage to the agricultural product may be predicted. In some embodiments, the data in the first feature set may be obtained by statistics, collection, or other means, for example, the current price of the agricultural product may be obtained by statistics. In some embodiments, the first set of characteristics may also include other data.

The preset time is an expected time of sale of the agricultural product. The preset time can be a certain time period, for example, 07: 00-09: 00 in a day, tuesday to thursday in a week, and july to september in a year; time points, for example, 7 o 'clock, 13 o' clock on 11 days of 11 months, etc., are also possible. In some embodiments, the preset time may be automatically generated by a predetermined promotion period, for example, day 1 of month 5, day 18 of month 6, and day 11 of month 11 of each year are automatically set as the preset time. In some embodiments, the preset time may be determined by parameters such as the ripening time and the preservation state of the agricultural product, for example, different preset times may be set for the early-maturing variety and the late-maturing variety, respectively, for different varieties of the same agricultural product. In some embodiments, the preset time may be obtained by a user or may be automatically generated by the system.

In some embodiments, data related to the agricultural product, such as a price of the agricultural product at a preset time, and the like, may be predicted and determined by various means, such as a model or an algorithm, based on characteristics related to the agricultural product, such as the first set of characteristics, and the like.

In some embodiments, a first predictive value for the agricultural commodity may be determined by the first model based on a first set of characteristics associated with the agricultural commodity, wherein the first set of characteristics includes at least one of a second predictive value for the agricultural commodity, a quality parameter for the agricultural commodity, and a current price for the agricultural commodity, the second predictive value being a rate of damage to the agricultural commodity.

The first model is a model for determining a first predicted value of the agricultural product. The first model may be a Neural Networks (NN) or the like model. For more description of the first model, refer to fig. 6 and its related description, which are not repeated herein.

The second predictive value is data related to the quality and extent of damage of the agricultural product, such as rate of damage of the agricultural product, freshness of the agricultural product, and the like. In some embodiments, the second predicted value may be a damage rate of the agricultural product, and the future quality state of the agricultural product and the like may be predicted based on the damage rate of the agricultural product and other parameters, and the price and other parameter data of the agricultural product at a preset time may be determined. In some embodiments, the second prediction value may also include other content.

The rate of deterioration is the rate at which the moisture level, nutritional level, visual integrity, freshness, etc. of the produce gradually loses, deteriorates over time and can be expressed in a number of ways, such as a grade, a value, etc., where the value can be a percentage, etc. In some embodiments, the rate of damage may be predicted by the second model. In some embodiments, the damage rate may be calculated by an algorithm. In some embodiments, the damage rate may also be statistically derived, among other ways. For more explanation on how to determine the damage rate, reference may be made to fig. 4 and its related description, which are not repeated herein.

The quality parameters are data related to the quality of agricultural products, such as the size of fruits, the sweetness of fruits, the color of fruits, the ratio of vegetable withered leaves, the content of nutrient components, and the like. In some embodiments, the quality parameter may be related to the agricultural product and other agricultural products associated therewith being viewed, purchased, and evaluated data, growth data. In some embodiments, the quality parameter may be determined according to physical and chemical characteristics of the agricultural product, for example, the quality parameter may be determined according to appearance, smell, sweetness, moisture content, and vitamin content of the fruit, and the quality parameter may be high if the appearance is good and the flavor is strong, the sweetness is high, and the vitamin content is high. In some embodiments, the quality parameter may be expressed in a grade or a numerical value. The quality parameter may be a quality grade or a quality score, etc. In some embodiments, the quality parameter may be determined based on a preset rule. The preset rule may be a rule preset in advance, for example, the preset rule may be a correspondence between various factors affecting the quality parameter and the quality parameter, and further, based on the preset rule and the various factors, specific contents of the quality parameter may be determined. In some embodiments, the quality parameter may be determined based on an algorithm or model, for example, by inputting various factors into the model to predict the quality parameter.

In some embodiments, the damage rate of the agricultural product, the current price of the agricultural product, and the quality parameter of the agricultural product may be input into the first model, the first model predicts a first predicted value, and the first predicted value may be the price of the agricultural product at a preset time. For example, the current price is the price of the agricultural product when the agricultural product is picked, and the first model judges the price of the agricultural product at a certain preset time after the freshness loss based on the damage rate and the quality parameters of the agricultural product at the moment. In some embodiments, the output of the first model may be a specific price at a preset time, and may also be an adjustment compared to the current price, such as a decrease, increase, decrease or increase in magnitude, etc.

In some embodiments, the other content may be determined by the first model based on the first set of characteristics. For example, the freshness cycle of the agricultural product, the expected sales of the agricultural product, etc. In some embodiments, the first prediction value may be determined based on other content. For example, the first predictive value is determined based on a reference price given by the merchant, the first predictive value is determined based on the sales volume, and so on.

Some embodiments of the present description predict and determine a price of an agricultural commodity over a period of time based on relevant characteristics of the agricultural commodity via a model. The mode can determine the future price of the agricultural product based on the current data of the agricultural product, so that the future pricing of the agricultural product is simpler and more efficient, and a targeted sales strategy can be rapidly formulated; the damage condition of future agricultural products can be determined based on the damage rate and the current quality of the agricultural products, so that differentiated pricing is carried out according to the damage condition of the agricultural products, a user can buy the products with the quality consistent with the price, the satisfaction degree of the user is improved, and the sale of the agricultural products is facilitated.

And step S304, determining the publicity content of the agricultural product at the preset time based on the second characteristic group related to the agricultural product. In some embodiments, this step S304 may be performed by the promotional content determination module 220.

The second characteristic group is data related to sales promotion of agricultural products, for example, growth data of agricultural products, a state of a preset time of agricultural products, a price of the preset time of agricultural products, a market saturation degree of agricultural products, and the like. In some embodiments, the second set of characteristics may include growth data of the agricultural commodity, a status of the agricultural commodity for a preset time, and the like, a price of the agricultural commodity for the preset time. In some embodiments, the data in the second feature set may be predicted, for example, by predicting a price for a preset time of the agricultural product. In some embodiments, the data in the second feature set may be obtained by statistics, collection, or other means, for example, growth data of the agricultural product may be obtained by collection. In some embodiments, the second set of characteristics may also include other data.

Promotional content is promotional information directed to the user, such as promotional posters, television advertisements, radio advertisements, pushed promotional information, and the like. In some embodiments, promotional content may be sent to the user in one or more of voice, text, image, and the like.

In some embodiments, promotional content for a preset time of an agricultural commodity may be determined based on a second set of characteristics associated with the agricultural commodity.

In some embodiments, a promotion strategy of the agricultural product preset time can be determined through a third model based on a second characteristic set, wherein the second characteristic set comprises at least one of the first predicted value, the state of the agricultural product preset time and growth data of the agricultural product; and then generating corresponding propaganda contents through a preset propaganda template based on the propaganda strategy. For a detailed description of the generation of the promotion content, reference may be made to fig. 5 and related contents, which are not described herein again.

Some embodiments of the present description may generate a promotional strategy via a model based on agricultural product-related characteristics. The method reduces the time for formulating the propaganda content, simplifies the process and reduces the cost of propaganda production. The method can also formulate means and modes according with actual sales propaganda of agricultural products according to future conditions of the agricultural products, reduces the probability of inconsistency of the propaganda contents with the actual propaganda contents, can formulate different propaganda contents aiming at the difference of the agricultural products, realizes differentiated sales strategies, ensures the sales rate, meets the differentiated requirements of different consumers and ensures that the propaganda aiming at different consumers is more accurate.

FIG. 4 is an exemplary flow chart of a method of determining a first predictive value for an agricultural product according to some embodiments described herein. The process 400 may be performed by the agricultural product automation management system 100. For example, the flow 400 may be performed by the processing device 120 described in fig. 1.

And S402, acquiring a second predicted value through the second model based on a third feature group related to the agricultural product. Wherein the third set of characteristics includes at least one of growth data of the agricultural product and environmental data of the agricultural product. In some embodiments, this step S402 may be performed by the second prediction value acquisition unit 221.

The second model is a model for determining the second predicted value, for example, a Neural Networks (NN) model. In some embodiments, a second predicted value for the agricultural product may be output by inputting one or a combination of growth data, environmental data, or a combination thereof for the agricultural product into the second model. In some embodiments, the second predictive value may be a rate of damage to the agricultural product.

The growth data of the agricultural products refer to data related to growth of the agricultural products in the whole process from planting to finishing. For example, growth data includes, but is not limited to: temperature, humidity, air quality, irrigation quantity, irrigation frequency, fertilization quantity, pesticide application condition and the like. In some embodiments, the growth data for the agricultural product may refer to data that may accelerate the deterioration of the agricultural product, and may include one or a combination of the time of harvest, whether a particular chemical agent was applied, the chemical composition of the soil at the stage of growth, and the like.

The environmental data of the agricultural product refers to data of physical environment during the growth and preservation of the agricultural product, such as the climate, temperature, humidity, season, weather and the like of the environment where the agricultural product grows and is stored. In some embodiments, the environmental data may be obtained by a sensor, a network, a storage device, a database, or a user terminal.

In some embodiments, the second predicted value may be obtained by the second model based on a third set of characteristics associated with the agricultural product, wherein the third set of characteristics may include at least one of growth data of the agricultural product and environmental data of the agricultural product. In some embodiments, the second predictive value may be a rate of damage, which is related to growth data and environmental data of the agricultural product, for example, the rate of damage may increase when the agricultural product is exposed to a humid, hot environment; when the produce is in a refrigerated, suitable environment, the rate of damage will remain low.

In some embodiments, there may be a correspondence between growth data and environmental data, for example, a high temperature and high humidity environment is favorable for rice growth, but during seedling growth, excessive precipitation may cause seedlings to lack oxygen, resulting in poor seedling development. In some embodiments, growth data for the agricultural product may be predicted based on environmental data of the agricultural product at different growth periods.

In some embodiments, the second predicted value may be obtained through calculation using an algorithm. In some embodiments, the second predicted value may also be obtained through other manners such as statistics, for example, the second predicted value is obtained through a database, a network, and direct input of a user.

In some embodiments, the first model and the second model type may be Neural Network (NN) or the like models, the second model output may be an input to the first model, and the first model and the second model may be jointly trained. In some embodiments, the second model outputs the second predicted value and inputs it to the first model to obtain the first predicted value. For more descriptions of the first model, the second model and the model training, refer to fig. 6 and related contents, which are not described herein again.

Some embodiments of the present description predict the damage rate of the agricultural product through a model, and determine the damage condition of the agricultural product after a period of time according to the damage rate and price. The damage rate determined in this way can be based on various data, so that the judgment of the damage rate is more comprehensive; a large amount of data can be quickly processed and utilized, so that a result can be obtained more quickly; the model can be trained by using historical data, so that the damage rate result is more accurate. The damage condition of the agricultural products after a period of time is predicted through the damage rate, the quality of the future agricultural products can be accurately judged based on the current data, differential pricing is favorably carried out on the agricultural products according to different damage conditions of the agricultural products, partial damaged agricultural products are favorably sold, the sale rate is improved, and the user can buy the products with the price matched with the quality.

Step S404, determining a first predicted value of the agricultural product based on a first feature set associated with the agricultural product. And the first predicted value is the price of the preset time of the agricultural product. In some embodiments, this step S404 may be performed by the first predictor determining module 210. For a detailed description of this step, refer to step S302 of fig. 3 and its related description, which are not repeated herein.

FIG. 5 is an exemplary flow diagram of a method for determining promotional content for a preset time of an agricultural product according to some embodiments of the present description. The process 500 may be performed by the agricultural product automation management system 100. For example, the flow 500 may be performed by the processing device 120 described in fig. 1.

And S502, determining a publicity strategy of agricultural product preset time through a third model based on the second feature group. Wherein the second characteristic group comprises at least one of the first predicted value, the state of the agricultural product in the preset time and the growth data of the agricultural product. In some embodiments, this step S502 may be performed by the promotional content determination module 220.

The propaganda strategy is a scheme for propaganda and sale of the agricultural products based on the current conditions of the agricultural products. In some embodiments, corresponding publicity strategies can be established according to the price, freshness, variety producing area, organic and inorganic properties and the like of agricultural products. For example, when the freshness of a certain agricultural product is poor, a publicity strategy taking low-price discount as the main part is made; when a certain agricultural product is close to the production date/picking date, a promotion strategy taking freshness as a leading factor is established.

The third model is a model for determining agricultural product promotion strategies, such as a Neural Networks (NN) model. For more description of the third model, refer to fig. 6 and its related description, which are not repeated herein.

The state of the preset time is the physical state of the agricultural product within the preset time. For example, whether the surface of the agricultural product is damaged by knocking, whether the agricultural product is rotten or rotten, whether the agricultural product has a bad smell, and the like. Through knowing the state of agricultural product preset time, can judge whether be fit for selling in the agricultural product preset time to and the propaganda strategy when formulating the sale.

In some embodiments, one or more information of the state of the agricultural product at the preset time, the first predicted value and the agricultural product growth data can be input into the third model, and the third model can output the promotion strategy of the agricultural product at the preset time. For example, when the surface of the input agricultural product is damaged by collision, the first predicted value is low, and after a chemical reagent is applied during the growth of the agricultural product, the third model outputs a promotion strategy which takes low price, discount and gift as the main part.

In some embodiments, the hyping policy may be formulated in other ways. For example, formulated based on user browsing, formulated based on search frequency, formulated based on merchants, formulated based on agricultural product network popularity, or the like. In some embodiments, the hype policy may be determined in a combination of the above manners, for example, after determining the hype policy using the model, the hype policy may be adjusted according to the search frequency of the keywords by the user, so as to highlight the keywords with high search frequency.

In some embodiments, the type of the third model may be an NN model, etc., the input of the third model may be a second feature set, the output may be one of price, freshness, and organic, which represents which is the promotion owner, the outputs of the first model and the second model are the input of the third model, and the first model, the second model, and the third model may be obtained through joint training. For more descriptions of the third model and the training of the model, reference may be made to the related description of fig. 6, which is not repeated herein.

In some embodiments, the state of the agricultural commodity at the preset time is associated with the second predicted value and the current state of the agricultural commodity. In some embodiments, the above relationship may be expressed by the following relationship:

y＝-kx+b

wherein y is the state of the agricultural product in the preset time (the agricultural product state can be quantized into numbers, the larger the y value is, the better the state of the agricultural product is, the smaller the y value is, the worse the state of the agricultural product is), k is the second predicted value, x is the time, and b is the current state of the agricultural product. According to the linear function, the preset time state of the agricultural product gradually becomes worse along with the time increase.

In some embodiments, the state of the agricultural product at the preset time, the second predicted value, and the current state of the agricultural product may be other forms of relationships, such as a quadratic function, a discrete function, a statistical relationship, and the like.

Step S504, based on the propaganda strategy, generating corresponding propaganda contents through a preset propaganda template. In some embodiments, this step S504 may be performed by the promotional content determination module 220.

The promotion template may be a preset template for agricultural product promotion. In some embodiments, the promotional template may be a text template, e.g., XX agricultural product is a harmless green organic environmental agricultural product, introduced variety, fresh environmental, XX agricultural product discounted price, buy a gift, etc. In some embodiments, the promotional templates may also be presented in other various forms, such as by picture, voice, video, and so forth.

In some embodiments, the corresponding promotional content may be generated through a preset promotional template based on the promotional strategy. In some embodiments, when the promotion strategy is determined to be low-price discount, a predetermined low-price discount promotion template in the system can be called and applied, and promotion content about the low-price discount of the agricultural product is generated.

In some embodiments, promotional content may be determined based on other content. E.g., based on the last promotional content, etc.

The beneficial effects that may be brought by the embodiments of the present description include, but are not limited to: the state of the agricultural products after a period of time is predicted through the model, the price of the agricultural products is adjusted, and corresponding propaganda strategies and propaganda contents are formulated, so that the sales mode and the propaganda contents are matched with the actual situation, the situation that the user considers that the reality is inconsistent with the propaganda is reduced, and the purchase experience of the user is improved.

It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, and any other advantages may be obtained.

It should be noted that the above descriptions of the processes 300, 400, and 500 are only for illustration and description, and do not limit the applicable scope of the present disclosure. Various modifications and changes to flow 300, flow 400, and flow 500 may occur to those skilled in the art upon reading the present specification. However, such modifications and variations are intended to be within the scope of the present description. For example, changes to the flow steps described herein, such as the addition of pre-processing steps and storage steps, may be made.

FIG. 6 is a block diagram of a model for a system for automated management according to some embodiments of the present description.

As shown in fig. 6, the model 600 may include a first model 601, a second model 602, and a third model 603.

In some embodiments, the first model 601 may be a model for determining a first predicted value of an agricultural product. In some embodiments, the first model 601 may be a Neural Networks (NN) or the like model. In some embodiments, the price 609 of the preset time of the agricultural product may be output by inputting the current price 608, the quality parameter 607, the damage rate 606, and the like of the agricultural product to the first model 601. In some embodiments, quality parameters 607 may be related to the agricultural product and other agricultural products associated therewith being viewed, purchased, and evaluated data, growth data. In some embodiments, the damage rate 606 may be obtained via the second model 602.

In some embodiments, the second model 602 may be a model for determining a second predicted value of the agricultural product. In some embodiments, the second model 602 may be a Neural Networks (NN) or the like model. In some embodiments, the rate of damage 606 of the agricultural product may be output by inputting environmental data 604, growth data 605, etc. of the agricultural product to the second model 602. In some embodiments, the environmental data 604 may be data of the physical environment in which the agricultural commodity is located, such as the climate, temperature, humidity, season, weather, etc. of the environment in which the agricultural commodity is located. In some embodiments, growth data 605 may be data that can accelerate agricultural product damage. Such as the time of harvest of the produce, whether a particular chemical agent has been applied, the chemical composition of the soil at the stage of growth, etc.

In some embodiments, the third model 603 may be a model for determining agricultural product promotion policies. In some embodiments, the third model 603 may be a Neural Networks (NN) or the like model. In some embodiments, the promotion policy 612 for the agricultural product may be output by inputting growth data 605 for the agricultural product, a preset time state 610, and a preset time price 609 into the third model 603. In some embodiments, the preset time state 610 is associated with the rate of damage 606 and the current state 611 of the agricultural product. In some embodiments, the input to the third model may also be added to a promotional template, and the output may be promotional content of the agricultural product.

In some embodiments, the first model may be obtained by separate training. For example, a sample damage rate of an agricultural product, a current sample price and a sample quality parameter are input into the first model to be used as training sample data, a price of the agricultural product preset time output by the first model is obtained, the price of the agricultural product preset time output by the first model is verified by using the price of the sample preset time as a label, and the trained first model is obtained through training. In some embodiments, the training input sample data and the label sample data of the first model may be obtained by various means, for example, historical data, real-time data acquisition, use of a model or algorithm, or the like, or combinations thereof.

In some embodiments, the second model may be obtained by separate training. For example, sample environment data and sample growth data of an agricultural product are input into the second model to serve as training sample data, the damage rate output by the second model is obtained, the sample damage rate serves as a label, the damage rate output by the second model is verified, and the trained second model is obtained through training. In some embodiments, the training input sample data and the label sample data of the second model may be obtained by various means, e.g., historical data, real-time data collection, etc., or a combination thereof.

In some embodiments, the output of the second model may be the input of the first model, and the first model and the second model may be obtained by joint training. For example, training sample data, namely sample environment data and sample growth data of agricultural products, are input into the second model, and the damage rate output by the second model is obtained; then, the damage rate is used as training sample data, the current price of the sample of the agricultural product and the quality parameters of the sample are input into the first model, the price of the agricultural product preset time output by the first model is obtained, and the price of the sample preset time is used for verifying the output of the first model; and obtaining the verification data of the damage rate output by the second model by utilizing the back propagation characteristic of the neural network model, and training the second model by using the verification data of the damage rate as a label. For another example, the training sample data includes sample environment data, sample growth data, a sample current price, and sample quality parameters of the agricultural product, the sample environment data and the sample growth data are input into the second model, the sample current price and the sample quality parameters are input into the first model, the output of the second model is used as the input of the first model, the label is the price of the sample preset time, and during the training process, the parameters of the model are updated by establishing a loss function based on the price of the sample preset time and the output of the second model.

In some embodiments, the third model may be obtained by separate training. For example, the sample growth data of the agricultural product, the sample preset time state and the price of the sample preset time are input into the third model and used as training sample data to obtain the publicity strategy of the agricultural product output by the third model, the publicity strategy of the agricultural product output by the third model is verified by using the sample publicity strategy as a label, and the trained third model is obtained through training. In some embodiments, the training sample data of the third model may be sample growth data of the agricultural product, a price of a sample preset time, a sample damage rate, and a sample current state, and the sample preset time state may be obtained from the sample damage rate and the sample current state. In some embodiments, the training sample data of the third model may be added to a sample promotion template, and the output may be promotion content of agricultural products. In some embodiments, the training input sample data and the label sample data of the third model may be obtained by various means, for example, historical data, data real-time collection, statistics, presets, use of a model or algorithm, or the like, or a combination thereof.

In some embodiments, the outputs of the first model and the second model may be inputs of a third model, and the first model, the second model, and the third model may be jointly trained. For example, training sample data, namely sample environment data and sample growth data of agricultural products, are input into the second model, and the damage rate output by the second model is obtained; then, the damage rate is used as training sample data, and the current price and the quality parameters of the agricultural product sample are input into the first model to obtain the price of the agricultural product preset time output by the first model; inputting the damage rate output by the second model, the price of the agricultural product preset time output by the first model, the sample growth data and the current state of the sample as training sample data into the third model to obtain a propaganda strategy output by the third model, and verifying the output of the third model by using the sample propaganda strategy; obtaining verification data of the damage rate output by the second model or verification data of the price of preset time output by the first model by utilizing the back propagation characteristic of the neural network model; and training the second model by using the verification data of the damage rate as a label, or training the first model by using the verification data of the preset time price as a label.

In some embodiments, the above functions of the first, second, and third models may be implemented by one, two, or another number of models.

Some embodiments of the present description may use joint training to derive the first model, the second model, and the third model. In the joint training, the accuracy of the intermediate results output by the single model, namely the damage rate and/or the price of the preset time, is no longer the focus, and only the final results obtained from the intermediate results, namely the price of the preset time or the accuracy of the publicity strategy, need to be concerned. The mode simplifies the training of the model, converts the individual training of the plurality of models into the training of the single model in the plurality of models, simplifies the training of the model, saves the training time of the model, lightens the workload of the model training, reduces the total steps of the training of the plurality of models, and leads the training of the model to be capable of focusing on the final result, namely the propaganda content of agricultural products, and not to focus on the intermediate result output by the single model. For a complex environment with a plurality of input features, the processing of the plurality of features can be converted into the processing of one of the features, the complex relation among the plurality of features which influence each other is simplified, the relation among any feature can be quickly established, the relation between the price and the publicity strategy of preset time of agricultural products which are influenced and determined by the plurality of features together can be conveniently determined, and the features can be growth data, environment data, damage rate, quality parameters and the like. The method greatly expands the applicable scenes of the models, and expands a plurality of models which are applicable to simple or fixed scenes into more complex and variable scenes.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.

Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.

Additionally, the order in which the elements and sequences of processes are described in this specification, the use of numerical letters, or the use of other names are not intended to limit the order of the processes and methods described in this specification, unless explicitly stated in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features than are expressly recited in a claim. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

For each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this specification, the entire contents of each are hereby incorporated by reference into this specification. Except where the application history document does not conform to or conflict with the contents of the present specification, it is to be understood that the application history document, as used herein in the present specification or appended claims, is intended to define the broadest scope of the present specification (whether presently or later in the specification) rather than the broadest scope of the present specification. It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.