Intelligent control system and method of ice making machine based on big data analysis

Abstract

The present invention belongs to the field of big data and intelligent control technology. An intelligent control system and method for an ice maker based on big data analysis are provided. The method comprises: in a first period, obtaining first operating big data of the merchant where the ice maker is deployed, and second operating big data of the business district where the merchant is located, predicting first expected operating data based on the first operating data prediction model of LSTM, and converting to obtain the first ice making amount, and controlling the ice maker to perform ice making operation; inputting the merchant's daily operating data into the second operating data prediction model based on LSTM, and obtaining the merchant's second expected operating data in the second period; converting the second ice making amount according to the remaining ice amount in the insulated box matched with the ice maker and the second expected operating data, and controlling the ice maker to perform supplementary ice making operation. The present invention can realize intelligent ice making of the ice maker without human participation.

Description

Technical Field

[0001] The present invention relates to the field of big data and intelligent control technology, and in particular to an intelligent control system and method for an ice making machine based on big data analysis. Background Art

[0002] Ice makers are widely used in food processing, catering services, cold chain logistics and other fields. They use different refrigeration technologies to make ice cubes. For example, ice makers are equipped in milk tea shops and coffee shops. The staff can input the ice production amount into the ice maker according to the business needs. The ice maker responds to prepare the corresponding amount of ice cubes and stores them in the insulated box for future use.

[0003] However, the manually input ice production amount is determined by the staff based on their business experience, and the final ice production amount may not be consistent with the actual business needs. If the ice production amount is too much, it will bring greater business costs to the business, while if the ice production amount is too little, it will cause customers to wait too long, which is not conducive to improving the consumer experience. How to improve the accuracy of ice production is a technical problem that needs to be solved at present. Summary of the invention

[0004] In this regard, the present invention provides an ice-making machine intelligent control method, system, electronic device, computer storage medium and computer program product based on big data analysis to solve the above technical problems.

[0005] The present invention provides an intelligent control method for an ice maker based on big data analysis, the method comprising the following steps: in a first time period, obtaining first business big data of a merchant where an ice maker is deployed, and second business big data of similar merchants in a business circle where the merchant is located, inputting the first business big data and the second business big data into a first business data prediction model based on LSTM to obtain first expected business data; converting a first ice making amount according to the first expected business data, and controlling the ice maker to perform ice making operations according to the first ice making amount; obtaining the merchant's day business data, inputting the day business data into a second business data prediction model based on LSTM to obtain second expected business data of the merchant in a second time period; wherein the second time period is later than the first time period; converting a second ice making amount according to the remaining ice amount in an insulation box matched with the ice maker and the second expected business data, and controlling the ice maker to perform supplementary ice making operations according to the second ice making amount.

[0006] In some embodiments, the obtaining of first business big data of the merchant where the ice maker is located, and second business big data of similar merchants in the business district where the merchant is located, includes: using a semantic analysis component to analyze the business attributes of the merchant, and performing semantic search at several designated data sources based on the business attributes obtained from the analysis; obtaining statistics on the number of similar business attributes in each time period based on the semantic search results, and calculating fluctuation data of the number of each similar business attribute, the fluctuation data including fluctuation amplitude and fluctuation frequency, and calculating an acquisition time according to the fluctuation data; obtaining the first business big data of the merchant where the ice maker is located according to the acquisition time, and obtaining the second business big data of the business district where the merchant is located according to the acquisition time.

[0007] In some embodiments, the calculating the acquisition duration according to the fluctuation data includes: introducing the fluctuation amplitude and the fluctuation frequency into the following calculation formula: ; In the above formula, is the acquisition duration, , The default basic acquisition duration is a constant value. For the The fluctuation range is is the mode of all the fluctuations, is the median of all the fluctuations mentioned, is the basic fluctuation range and is a constant value; is the fluctuation frequency, is the basic fluctuation frequency and is a constant value.

[0008] In some embodiments, the inputting of the day's business data into a second business data prediction model based on LSTM to obtain the second expected business data of the merchant in the second time period includes: inputting the day's business data into a second business data prediction model based on LSTM to obtain the third expected business data of the merchant in the second time period; calculating the remaining time between the end of the second time period and the end of business of the merchant, calculating an adjustment coefficient based on the remaining time, and using the adjustment coefficient to correct the third expected business data to obtain the second expected business data; wherein, the second expected business data = the third expected business data * (1 + adjustment coefficient).

[0009] In some embodiments, the second ice making amount is calculated based on the remaining ice amount in the insulation box matched with the ice maker and the second expected operating data, and the ice maker is controlled to perform supplementary ice making operations according to the second ice making amount, including: calculating a third ice making amount based on the second expected operating data, and judging whether the third ice making amount is greater than the remaining ice making amount; if the third ice making amount is greater than the remaining ice making amount, calculating the difference between the third ice making amount and the remaining ice making amount to obtain the second ice making amount, and controlling the ice maker to perform supplementary ice making operations according to the second ice making amount; if the third ice making amount is not greater than the remaining ice making amount, the ice maker is not controlled to perform supplementary ice making operations.

[0010] In some embodiments, the inputting of the first business big data and the second business big data into a first business data prediction model based on LSTM to obtain first expected business data includes: using the convolutional network module of the first business data prediction model to perform feature extraction on the first business big data and the second business big data respectively to obtain first business features and second business features; inputting the first business features and the second business features into the LSTM module of the first business data prediction model to obtain the predicted first expected business data.

[0011] The present invention also provides an intelligent control system for an ice maker based on big data analysis, the system comprising a processing module and a storage module, the computer code stored in the storage module being called and executed by the processing module to implement the following steps: in a first time period, obtaining first business big data of a merchant where the ice maker is deployed, and second business big data of similar merchants in the business district where the merchant is located, inputting the first business big data and the second business big data into a first business data prediction model based on LSTM to obtain first expected business data; converting a first ice making amount according to the first expected business data, and controlling the ice maker to perform ice making operations according to the first ice making amount; obtaining the merchant's day business data, inputting the day business data into a second business data prediction model based on LSTM to obtain second expected business data of the merchant in a second time period; wherein the second time period is later than the first time period; converting a second ice making amount according to the remaining ice amount in an insulation box matched with the ice maker and the second expected business data, and controlling the ice maker to perform supplementary ice making operations according to the second ice making amount.

[0012] The present invention also provides an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in any of the preceding items.

[0013] The present invention also provides a computer storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method as described in any of the above items.

[0014] The present invention also provides a computer program product, which includes a computer program stored in a computer storage medium, and when the computer program is executed by a processor of an electronic device, it implements the method described in any of the above items.

[0015] The beneficial effects of the present invention are as follows: the intelligent ice-making machine of the present invention can decide by itself the amount of ice that should be prepared to meet the business needs of the merchant through big data analysis technology, without the need to manually set the amount of ice made, thereby improving business efficiency; and, because the predicted amount of ice made is more accurate than the amount of ice made determined based on experience, it can also avoid the problems of increased costs and long waiting times for customers caused by making too much or too little ice. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of an ice-making machine intelligent control method based on big data analysis disclosed in an embodiment of the present invention.

[0018] Figure 2 It is a structural diagram of the first business data prediction model disclosed in an embodiment of the present invention.

[0019] Figure 3 It is a structural schematic diagram of an ice-making machine intelligent control system based on big data analysis disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0021] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0022] like Figure 1 As shown, an embodiment of the present invention discloses an intelligent control method for an ice maker based on big data analysis, the method comprising the following steps: in a first time period, obtaining first business big data of a merchant where the ice maker is deployed, and second business big data of similar merchants in the business district where the merchant is located, inputting the first business big data and the second business big data into a first business data prediction model based on LSTM to obtain first expected business data; converting a first ice making amount according to the first expected business data, and controlling the ice maker to perform ice making operations according to the first ice making amount; obtaining the merchant's business data for the day, inputting the business data for the day into a second business data prediction model based on LSTM to obtain second expected business data of the merchant in the second time period; wherein the second time period is later than the first time period; converting a second ice making amount according to the remaining ice amount in the insulation box matched with the ice maker and the second expected business data, and controlling the ice maker to perform supplementary ice making operations according to the second ice making amount.

[0023] The ice maker deployed in the merchant of the present invention is an intelligent ice maker, which can decide how much ice should be prepared to meet the business needs of the merchant, and can decide the amount of ice to be supplemented according to the actual business situation of the merchant on that day. Specifically, in the first period, the first business big data of the merchant where the ice maker is deployed and the second business big data of similar merchants in the business district where the merchant is located are first obtained. Among them, the first business big data and the second business big data include the sales volume of the business items using ice cubes for the merchant and other similar merchants in the business district, such as the sales volume of iced milk tea. The first business data prediction model based on LSTM is used to conduct an in-depth analysis of the first business big data and the second business big data obtained, and the first expected business data of the merchant can be obtained. Since the single ice demand of the business items using ice cubes is generally fixed, the first ice making amount can be converted according to the first expected business data and the single ice demand, and the ice maker is controlled to make ice according to the first ice making amount, so that the business needs of the merchant in the first period of the day can be met.

[0024] At the same time, the present invention also obtains the merchant's business data for the day, and uses the second business data prediction model based on LSTM to conduct an in-depth analysis of the business data for the day, so as to obtain the second expected business data of the merchant in the next second time period, and the amount of ice that needs to be replenished, i.e., the second ice making amount, can be calculated according to the remaining ice amount in the insulated box matched with the ice maker, the second expected business data and the single ice demand, and the ice maker is controlled to perform the replenishment ice making operation according to the second ice making amount, and so on and so forth, so as to meet the merchant's business needs for the day.

[0025] Therefore, the intelligent ice-making machine of the present invention can decide on its own the amount of ice that should be prepared to meet the business needs of the merchant through big data analysis technology, without the need to manually set the ice-making amount, thereby improving business efficiency; moreover, since the predicted ice-making amount is more accurate than the ice-making amount determined based on experience, it can also avoid the problems of increased costs and long waiting times for customers caused by making too much or too little ice.

[0026] The first time period is, for example, the morning of each business day, that is, after the business hours of each day are reached, the ice maker automatically analyzes and obtains the first ice production amount, and then automatically prepares ice cubes of the first ice production amount. The second time period is, for example, the noon period, afternoon period, and evening period of each business day, that is, after the noon period / afternoon period / evening period of each day is about to be reached, the ice maker predicts the first ice production amount based on the actual operating data of the day and the remaining ice volume in the insulated box, and then automatically prepares supplementary ice cubes of the second ice production amount.

[0027] In some embodiments, the obtaining of first business big data of the merchant where the ice maker is located, and second business big data of similar merchants in the business district where the merchant is located, includes: using a semantic analysis component to analyze the business attributes of the merchant, and performing semantic search at several designated data sources based on the business attributes obtained from the analysis; obtaining statistics on the number of similar business attributes in each time period based on the semantic search results, and calculating fluctuation data of the number of each similar business attribute, the fluctuation data including fluctuation amplitude and fluctuation frequency, and calculating an acquisition time according to the fluctuation data; obtaining the first business big data of the merchant where the ice maker is located according to the acquisition time, and obtaining the second business big data of the business district where the merchant is located according to the acquisition time.

[0028] In an embodiment of the present invention, the present invention needs to analyze the business big data of the merchant and other similar merchants in the business district where the merchant is located to obtain the first expected business data of the merchant in the first time period. At this time, it is necessary to determine the data volume of the business big data, that is, what time span should be used to obtain the business big data.

[0029] In view of the above practical problems, the present invention is configured to first use a semantic analysis component to analyze the business attributes of the merchant, that is, to analyze what kind of business the merchant is engaged in, such as milk tea shop, coffee shop, restaurant, etc. Based on the business attributes obtained by the analysis, a semantic search is performed at several designated data sources, that is, a semantic search is performed at designated data sources such as review websites and chat community APPs with milk tea shop, coffee shop, restaurant, etc. as keywords, so as to obtain the number of similar business attributes in each time period, and further calculate the fluctuation data of the number of each similar business attribute, including the fluctuation amplitude and the fluctuation frequency. Finally, the acquisition time is calculated based on the calculated fluctuation data, and the acquisition time is the aforementioned time span. According to the time span, the first business big data of the merchant where the ice machine is deployed and the second business big data of the business district where the merchant is located are obtained. The acquisition time is, for example, 1 month, 3 months, half a year, etc.

[0030] In some embodiments, the calculating the acquisition duration according to the fluctuation data includes: introducing the fluctuation amplitude and the fluctuation frequency into the following calculation formula: ; In the above formula, is the acquisition duration, , The default basic acquisition duration is a constant value. For the The fluctuation range is is the mode of all the fluctuations, is the median of all the fluctuations mentioned, is the basic fluctuation range and is a constant value; is the fluctuation frequency, is the basic fluctuation frequency and is a constant value.

[0031] Referring to the expression of the above calculation formula, the acquisition time and fluctuation amplitude in the present invention are The mean, the difference between the mode and the median of the fluctuation range, and the fluctuation frequency The larger the difference, the higher the volatility, which means the more unstable the operating data is. The larger the value, the more unstable the business data. The number of merchants of this type shows great volatility overall. Correspondingly, set the acquisition time. Smaller, that is, it is preferred to use "recent" (for example, within 30 days) business big data. Conversely, the smaller the difference, the lower the volatility, indicating that the business data is more stable and the frequency of fluctuations is higher. The smaller the value, the more stable the business data. The number of merchants of this type shows great volatility overall. Correspondingly, set the acquisition time. Larger, that is, it is preferred to use "medium- to long-term" (for example, within 90 days) business big data. In this way, it is possible to ensure that the appropriate amount of first business big data and second business big data are obtained through dynamically changing acquisition time, thereby ensuring the accuracy of the first expected business data obtained by subsequent analysis.

[0032] In some embodiments, the inputting of the day's business data into a second business data prediction model based on LSTM to obtain the second expected business data of the merchant in the second time period includes: inputting the day's business data into a second business data prediction model based on LSTM to obtain the third expected business data of the merchant in the second time period; calculating the remaining time between the end of the second time period and the end of business of the merchant, calculating an adjustment coefficient based on the remaining time, and using the adjustment coefficient to correct the third expected business data to obtain the second expected business data; wherein, the second expected business data = the third expected business data * (1 + adjustment coefficient).

[0033] In an embodiment of the present invention, the present invention uses a second business data prediction model based on LSTM to perform predictive analysis on the merchant's business data for the day, wherein the business data for the day refers to the business data of each time period (e.g., half an hour) after the merchant starts business on the day. The second business data prediction model can predict the third expected business data of the merchant in the second time period based on these time period business data arranged in chronological order.

[0034] However, the third expected business data is a theoretical value. If the second ice-making amount is determined only according to the third expected business data, it is easy to have insufficient actual ice available. In this regard, the present invention further calculates the remaining time between the end of the second time period and the end of business of the merchant, calculates the adjustment coefficient based on the remaining time, and then uses the adjustment coefficient to correct the third expected business data, and finally obtains the second expected business data that is more in line with the actual situation. Among them, the adjustment coefficient is positively correlated with the remaining time, that is, the closer to the end of business, the smaller the adjustment coefficient is set, that is, the incremental adjustment of the third expected business data is weakened, and vice versa. With such a setting, the waste of ice cubes can be minimized while meeting the demand for ice.

[0035] In some embodiments, the second ice making amount is calculated based on the remaining ice amount in the insulation box matched with the ice maker and the second expected operating data, and the ice maker is controlled to perform supplementary ice making operations according to the second ice making amount, including: calculating a third ice making amount based on the second expected operating data, and judging whether the third ice making amount is greater than the remaining ice making amount; if the third ice making amount is greater than the remaining ice making amount, calculating the difference between the third ice making amount and the remaining ice making amount to obtain the second ice making amount, and controlling the ice maker to perform supplementary ice making operations according to the second ice making amount; if the third ice making amount is not greater than the remaining ice making amount, the ice maker is not controlled to perform supplementary ice making operations.

[0036] In the embodiment of the present invention, the third ice making amount can be converted according to the second expected operating data in the same manner as described above, and the third ice making amount is the predicted ice demand in the second time period. If the third ice making amount is greater than the remaining ice amount, it means that the remaining ice in the insulated box matched with the ice maker is insufficient to support the demand for ice in the second time period, and it is necessary to perform additional ice making operations, that is, the difference between the third ice making amount and the remaining ice amount is calculated to obtain the second ice making amount, and the ice maker is controlled to prepare ice cubes of the second ice making amount. If the third ice making amount is not greater than the remaining ice amount, it means that the remaining ice in the insulated box matched with the ice maker is sufficient to support the demand for ice in the second time period, and it is not necessary to perform additional ice making operations.

[0037] In some embodiments, the inputting of the first business big data and the second business big data into a first business data prediction model based on LSTM to obtain first expected business data includes: using the convolutional network module of the first business data prediction model to perform feature extraction on the first business big data and the second business big data respectively to obtain first business features and second business features; inputting the first business features and the second business features into the LSTM module of the first business data prediction model to obtain the predicted first expected business data.

[0038] In an embodiment of the present invention, the first business data prediction model in the present invention combines LSTM and convolutional network, wherein the convolutional network is used to extract the first business feature and the second business feature that characterize the business law of the business attribute from the first business big data and the second business big data, and then the LSTM module predicts and analyzes the first business feature and the second business feature, thereby obtaining the first expected business data. In other words, the first business data prediction model in the present invention includes a convolutional network module and an LSTM module, such as Figure 2 shown.

[0039] like Figure 3As shown, an embodiment of the present invention further discloses an intelligent control system for an ice maker based on big data analysis, the system comprising a processing module and a storage module, the computer code stored in the storage module being called and executed by the processing module to implement the following steps: in a first time period, obtaining first business big data of the merchant where the ice maker is deployed, and second business big data of similar merchants in the business district where the merchant is located, inputting the first business big data and the second business big data into a first business data prediction model based on LSTM to obtain first expected business data; converting a first ice making amount according to the first expected business data, and controlling the ice maker to perform ice making operations according to the first ice making amount; obtaining the merchant's business data for the day, inputting the business data for the day into a second business data prediction model based on LSTM to obtain the merchant's second expected business data for the second time period; wherein the second time period is later than the first time period; converting a second ice making amount according to the remaining ice amount in the insulation box matched with the ice maker and the second expected business data, and controlling the ice maker to perform supplementary ice making operations according to the second ice making amount.

[0040] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in the above embodiment.

[0041] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the above embodiment.

[0042] The embodiment of the present invention further discloses a computer program product. When the computer program product is run on a terminal, the terminal implements the method described in the above embodiment.

[0043] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0044] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0045] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0046] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. An intelligent control method for ice making machine based on big data analysis, characterized in that: The method comprises the following steps: in a first time period, obtaining first business big data of the merchant where the ice-making machine is deployed, and second business big data of similar merchants in the business circle where the merchant is located, inputting the first business big data and the second business big data into a first business data prediction model based on LSTM to obtain first expected business data; converting a first ice-making amount according to the first expected business data, and controlling the ice-making machine to perform ice-making operations according to the first ice-making amount; obtaining the merchant's business data for the day, inputting the business data for the day into a second business data prediction model based on LSTM, and obtaining the merchant's second expected business data for the second time period; wherein the second time period is later than the first time period; converting a second ice-making amount according to the remaining ice amount in the insulation box matched with the ice-making machine and the second expected business data, and controlling the ice-making machine to perform supplementary ice-making operations according to the second ice-making amount; The method comprises the following steps: obtaining first business big data of a merchant where an ice maker is installed, and second business big data of similar merchants in a business district where the merchant is located, comprising: analyzing the business attributes of the merchant using a semantic analysis component, and performing semantic search at several designated data sources based on the business attributes obtained by the analysis; obtaining the number of similar business attributes in each time period based on the semantic search results, and calculating fluctuation data of the number of each similar business attribute, wherein the fluctuation data includes fluctuation amplitude and fluctuation frequency, and calculating an acquisition time according to the fluctuation data; obtaining the first business big data of the merchant where the ice maker is installed according to the acquisition time, and obtaining the second business big data of the business district where the merchant is located according to the acquisition time; wherein the acquisition time is negatively correlated with the fluctuation frequency.

2. The ice making machine intelligent control method based on big data analysis according to claim 1 is characterized in that: Calculating the acquisition duration according to the fluctuation data includes: introducing the fluctuation amplitude and the fluctuation frequency into the following calculation formula: ; In the above formula, is the acquisition duration, The default basic acquisition duration is a constant value. is the i-th fluctuation amplitude, is the mode of all the fluctuations, is the median of all the fluctuations mentioned, is the basic fluctuation range and is a constant value; is the fluctuation frequency, is the basic fluctuation frequency and is a constant value.

3. The ice making machine intelligent control method based on big data analysis according to claim 2 is characterized in that: Inputting the day's business data into a second business data prediction model based on LSTM to obtain the second expected business data of the merchant in the second time period, including: inputting the day's business data into a second business data prediction model based on LSTM to obtain the third expected business data of the merchant in the second time period; calculating the remaining time between the end of the second time period and the end of business of the merchant, calculating an adjustment coefficient based on the remaining time, and using the adjustment coefficient to correct the third expected business data to obtain the second expected business data; wherein, the second expected business data = the third expected business data * (1 + adjustment coefficient).

4. The ice making machine intelligent control method based on big data analysis according to claim 3 is characterized in that: A second ice making amount is calculated based on the remaining ice amount in the insulation box matched with the ice maker and the second expected operating data, and the ice maker is controlled to perform supplementary ice making operations according to the second ice making amount, including: a third ice making amount is calculated based on the second expected operating data, and whether the third ice making amount is greater than the remaining ice amount; if the third ice making amount is greater than the remaining ice amount, the difference between the third ice making amount and the remaining ice amount is calculated to obtain the second ice making amount, and the ice maker is controlled to perform supplementary ice making operations according to the second ice making amount; if the third ice making amount is not greater than the remaining ice amount, the ice maker is not controlled to perform supplementary ice making operations.

5. The ice making machine intelligent control method based on big data analysis according to claim 4 is characterized in that: Inputting the first business big data and the second business big data into a first business data prediction model based on LSTM to obtain first expected business data, including: using the convolutional network module of the first business data prediction model to perform feature extraction on the first business big data and the second business big data respectively to obtain first business features and second business features; inputting the first business features and the second business features into the LSTM module of the first business data prediction model to obtain the predicted first expected business data.

6. An intelligent control system for ice making machines based on big data analysis, the system being based on the method according to any one of claims 1 to 5, the system comprising a processing module and a storage module, characterized in that: The computer code stored in the storage module is called and executed by the processing module to implement the following steps: in a first time period, obtaining first business big data of the merchant where the ice maker is deployed, and second business big data of similar merchants in the business district where the merchant is located, inputting the first business big data and the second business big data into a first business data prediction model based on LSTM to obtain first expected business data; calculating a first ice making amount according to the first expected business data, and controlling the ice maker to perform ice making operations according to the first ice making amount; obtaining the merchant's daily business data, inputting the daily business data into a second business data prediction model based on LSTM to obtain second expected business data of the merchant in a second time period; wherein the second time period is later than the first time period; calculating a second ice making amount according to the remaining ice amount in the insulation box matched with the ice maker and the second expected business data, and controlling the ice maker to perform supplementary ice making operations according to the second ice making amount.

7. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 5.

8. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program stored in a computer storage medium, characterized in that: When the computer program is executed by a processor of an electronic device, the method according to any one of claims 1 to 5 is implemented.

Images