Refrigeration prediction management system based on big data analysis

Abstract

The invention relates to the technical field of personnel management, in particular to a refrigeration prediction management system based on big data analysis. The system comprises an environment fitness recognition module, an interest preference route prediction module, an intelligent interaction guide shunting module and a cooling capacity adjustment comprehensive management module, and the environment fitness recognition module collects sensitivity information of consumers to temperature and recognizes people intolerance of cold constitution and people intolerance of hot constitution according to the sensitivity information; according to the refrigeration prediction management system based on big data analysis, two routes going to the same destination are obtained by predicting the route directions of consumers after walking out of different elevators, and connection with the elevators of the shopping mall is established to guide the consumers with different physiques, so that the consumers with different physiques are located in different routes, and the refrigeration efficiency is improved. Therefore, the cooling capacity is adjusted according to different routes, the purpose of saving energy is achieved, and the shopping experience of consumers is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of personnel management, and in particular to a refrigeration prediction management system based on big data analysis. Background Art

[0002] A shopping mall is a comprehensive commercial facility that usually includes multiple retail stores, service facilities and entertainment venues, aiming to provide consumers with a one-stop shopping, dining, leisure and entertainment experience. The size of a shopping mall can range from a smaller community shopping mall to a large super-regional shopping mall, and its business formats also cover a variety of forms, from large department stores and supermarkets to various specialty stores, restaurants, cinemas, etc.

[0003] Refrigeration is a way of cooling down. It can keep the indoor temperature within a comfortable range, providing customers and employees with a comfortable shopping and working environment regardless of how the weather changes outside.

[0004] At present, most shopping malls usually allocate cooling systems by identifying areas where people gather, and distribute more cold air to the gathering areas to avoid the temperature in the area from rising. However, when facing some shopping malls with a large number of people, the traditional cooling system allocation method faces severe challenges. Since a large number of consumers gather in shopping malls, and each consumer has different physiques, some consumers are afraid of heat, while others are afraid of cold. At the same time, consumers are always on the move, which can easily cause consumers with different physiques to mix, making the allocation of cooling systems more difficult. On the one hand, it is not conducive to energy saving, and on the other hand, it also affects the shopping experience of some consumers. Summary of the invention

[0005] The purpose of the present invention is to provide a refrigeration prediction management system based on big data analysis to solve the problems raised in the above background technology.

[0006] To achieve the above objectives, a refrigeration prediction management system based on big data analysis is provided, including an environmental adaptability identification module, an interest preference route prediction module, an intelligent interactive guidance diversion module, and a cooling capacity regulation comprehensive management module, wherein:

[0007] The environmental adaptability identification module collects consumers' sensitivity information to temperature, and identifies people with cold-fearing constitution and people with heat-fearing constitution according to the sensitivity information;

[0008] The interest preference route prediction module obtains two different routes for consumers to go to the desired destination based on the consumer's behavior habits, obtains the corresponding relationship between the two different routes and each elevator in the shopping mall, and binds the corresponding elevator to the corresponding route;

[0009] The intelligent interactive guidance and diversion module establishes a human-computer interactive control platform, collects information about the destination that consumers need to go to, and guides consumers with different physical conditions to the elevators corresponding to different routes;

[0010] The cooling capacity regulation integrated management module monitors the positions of consumers on two different routes in real time, and regulates and manages the cooling capacity on the two different routes according to the consumers' physical fitness information.

[0011] As a further improvement of the technical solution, the method steps for the environmental adaptability recognition module to recognize people with cold-fearing physique and people with heat-fearing physique are as follows:

[0012] S100A, establish a cold-fear behavior database to record people's cold-fear posture information;

[0013] S100B, establishing a communication connection with the monitoring equipment in the mall, and using the monitoring equipment to obtain image information inside the mall;

[0014] S100C, monitoring the posture information of the consumer through the screen information, and when the posture information of the consumer is consistent with the posture information of fear of cold, marking the consumer as having a cold-fearing physique; when the posture information of the consumer is different from the posture information of fear of cold, marking the consumer as having a heat-fearing physique.

[0015] As a further improvement of the technical solution, the method steps for the interest preference route prediction module to obtain two different routes are as follows:

[0016] S200A, obtaining multiple routes for different consumers to enter the same store;

[0017] S200B, randomly selecting two routes from the multiple routes, and calculating the similarity between the two routes;

[0018] S200C: When the two routes are not similar, return to S200B; when the two routes are not similar, mark the two routes as route one and route two, respectively.

[0019] As a further improvement of the technical solution, the method steps for calculating the similarity of two routes in S200B are as follows:

[0020] S2.1, define two routes as the first route and the second route respectively;

[0021] S2.2. Obtain all environmental information around the first route h ambient ;

[0022] S2.3. Obtain the common environmental information S around the second route and the first route ambient ;

[0023] S2.4. Set similarity threshold S t h res h old , when the similarity threshold S t h res h old ≤ The environmental information S shared by the second route and the first route ambient / All environmental information around the first route F ambient When , it indicates that the first route is similar to the second route. When the similarity threshold S t h res h old > Environmental information S shared by the second route and the first route ambient / All environmental information around the first route F ambient , indicating that the first route and the second route are not similar.

[0024] As a further improvement of the technical solution, the method steps for the interest preference route prediction module to bind the corresponding elevator with the corresponding route are as follows:

[0025] S200D, retrieve the monitoring screen of the monitoring equipment near the elevator;

[0026] S200E: Collect the number of consumers who move to route 1 after exiting the elevator C route1 and the number of moves to route 2 C route2 ;

[0027] S200F, set binding threshold B t h res h old , when moving to route 1, the number C route1 > Binding threshold B t h res h old When the elevator is bound to route 1, it will be bound to route 1. When it moves to route 2, the number C route2 > Binding threshold B threshoold , bind the elevator to route 2.

[0028] As a further improvement of the technical solution, the method steps for the intelligent interaction guidance and diversion module to establish a human-computer interaction control platform are as follows:

[0029] S300A, set up a human-computer interaction terminal at the entrance of the shopping mall;

[0030] S300B, cancel the control of the elevator by the control button, and establish a communication control connection with the elevator through the human-computer interaction terminal;

[0031] S300C, collecting the consumer's destination, obtaining route 1 and route 2 to the destination, and elevators corresponding to route 1 and route 2;

[0032] S300D, obtaining the physical condition information of the consumers, guiding all the consumers with a cold-sensitive constitution to the elevator corresponding to one of the routes in S300C, and guiding all the consumers with a heat-sensitive constitution to the elevator corresponding to another route in S300C;

[0033] S300E: When the consumer interacting with the human-machine interaction terminal enters the corresponding elevator, the elevator is controlled to rise to the floor corresponding to the destination.

[0034] As a further improvement of this technical solution, the following method steps are also included:

[0035] S300F, setting a threshold for the number of people taking the elevator, when the number of consumers guided into the elevator is greater than the threshold for the number of people taking the elevator, controlling the elevator to rise to the floor corresponding to the destination;

[0036] S300G, set up an elevator reminder program to predict the time when the elevator will reach the threshold number of passengers based on the passenger flow, and notify consumers.

[0037] As a further improvement of this technical solution, the following method steps are also included:

[0038] S300H. When consumers corresponding to route one move to route two, the human-computer interaction terminal guides consumers with the same physique to the elevator corresponding to route two; when consumers corresponding to route two move to route one, the human-computer interaction terminal guides consumers with the same physique to the elevator corresponding to route one.

[0039] As a further improvement of the technical solution, the method steps for the cooling capacity regulation integrated management module to regulate and manage the cooling capacity on two different routes are as follows:

[0040] S400A, obtaining the route of the consumer with a cold-sensitive constitution, and adjusting the cold wind on the route to weak wind;

[0041] S400B, obtaining the route of the consumer with a heat-phobic constitution, and adjusting the cold wind on the route to strong wind;

[0042] S400C. Obtain the locations of consumers with a cold-sensitive constitution and consumers with a heat-sensitive constitution. When the consumers with a cold-sensitive constitution and consumers with a heat-sensitive constitution meet, adjust the weak wind on the original route to a strong wind, and adjust the strong wind on the original route to a weak wind.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] 1. In the refrigeration prediction management system based on big data analysis, two routes to the same destination are obtained by predicting the directions of consumers after they walk out of different elevators, and a connection is established with the elevators of the shopping mall to guide consumers with different physiques and put them on different routes. The cooling capacity is adjusted according to the different routes, which not only achieves the purpose of energy saving, but also improves the shopping experience of consumers.

[0045] 2. In the refrigeration prediction management system based on big data analysis, since the stores around the two routes are different, after consumers have visited the stores around the corresponding route, consumers with different physiques will be attracted to the other route, reducing the consumers' stay in the original route, thereby avoiding the phenomenon of large-scale mixing between consumers with different physiques and improving the feasibility of adjusting the cooling capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A block diagram of the overall modules of the present invention;

[0047] Figure 2 The state diagram of route 1 and route 2 of the present invention is shown in FIG. Figure 1 ;

[0048] Figure 3 The state diagram of route 1 and route 2 of the present invention is shown in FIG. Figure 2 .

[0049] The meaning of each number in the figure is:

[0050] 100. Environmental adaptability identification module; 200. Interest preference route prediction module; 300. Intelligent interactive guidance and diversion module; 400. Cold capacity regulation integrated management module. DETAILED DESCRIPTION

[0051] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0053] See also Figure 1-Figure 3As shown, a refrigeration prediction management system based on big data analysis is provided, including an environmental adaptability recognition module 100, an interest preference route prediction module 200, an intelligent interactive guidance diversion module 300, and a cooling capacity adjustment comprehensive management module 400, wherein:

[0054] The environmental adaptability identification module 100 collects the consumer's sensitivity information to temperature, and identifies people with a cold-fearing constitution and people with a heat-fearing constitution based on the sensitivity information;

[0055] The interest preference route prediction module 200 obtains two different routes for consumers to go to the desired destination through the consumer's behavior habits, obtains the corresponding relationship between the two different routes and each elevator in the shopping mall, and binds the corresponding elevator to the corresponding route;

[0056] The intelligent interactive guidance and diversion module 300 establishes a human-machine interactive control platform, collects information about the destination that consumers need to go to, and guides consumers with different physical conditions to the elevators corresponding to different routes;

[0057] The cooling capacity regulation integrated management module 400 monitors the locations of consumers on two different routes in real time, and regulates and manages the cooling capacity on the two different routes according to the consumers' physical fitness information.

[0058] In other words, by predicting the directions of consumers' routes after they walk out of different elevators, we can get two routes to the same destination, and establish a connection with the elevators in the mall to guide consumers with different physical conditions and put them on different routes. The cooling amount can be adjusted according to the different routes, which not only achieves the purpose of energy saving, but also improves the shopping experience of consumers.

[0059] In the above, the method steps of the environmental adaptability identification module 100 for identifying people with a cold-fearing constitution and people with a heat-fearing constitution are as follows:

[0060] S100A, establish a cold-fear behavior database to record people's cold-fear posture information, such as shivering, curling up, or putting hands in pockets to keep warm;

[0061] S100B, establishing a communication connection with the monitoring equipment in the mall, and using the monitoring equipment to obtain image information inside the mall;

[0062] S100C, monitoring the posture information of the consumer through the screen information, when the posture information of the consumer is consistent with the posture information of fear of cold, marking the consumer as having a constitution of fear of cold; when the posture information of the consumer is different from the posture information of fear of cold, marking the consumer as having a constitution of fear of heat.

[0063] For example, consumer A and consumer B are shopping in a mall, but consumer A often shivers or shrinks his body during the shopping process. In this case, consumer A can be marked as having a cold-sensitive physique; while consumer B does not shiver or shrink his body during the shopping process. In this case, consumer B can be marked as having a heat-sensitive physique.

[0064] In addition, the method steps for the interest preference route prediction module 200 to obtain two different routes are as follows:

[0065] S200A, obtaining multiple routes for different consumers to enter the same store;

[0066] S200B, randomly selecting two routes from the multiple routes, and calculating the similarity between the two routes;

[0067] S200C: When the two routes are not similar, return to S200B; when the two routes are not similar, mark the two routes as route one and route two, respectively.

[0068] Specifically, for example, there are three consumers, A, B, and C, in a shopping mall. Consumer A enters store A through the first route, consumer B enters store A through the second route, and consumer C enters store A through the third route. At this time, two routes are randomly selected from these three routes for similarity comparison. Assuming that the first route and the third route are not similar, the first route is marked as route one, and the third route is marked as route two.

[0069] Furthermore, the method steps for calculating the similarity of two routes in S200B are as follows:

[0070] S2.1, define two routes as the first route and the second route respectively;

[0071] S2.2. Obtain all environmental information around the first route F ambient ;

[0072] S2.3. Obtain the common environmental information S around the second route and the first route ambient ;

[0073] S2.4. Set similarity threshold S t h res h old , when the similarity threshold S t h res h old ≤ The environmental information S shared by the second route and the first route ambient / All environmental information around the first route F ambient When , it indicates that the first route is similar to the second route. When the similarity threshold S t hres h old > Environmental information S shared by the second route and the first route ambient / All environmental information around the first route F ambient , indicating that the first route and the second route are not similar.

[0074] For example, the environmental information around the first route F ambient There are coffee shops, tea shops, clothing shops, etc.; the surrounding environment information of the second route includes mobile phone shops, car shops, and computer shops. Then the surrounding environment information S of the second route and the surrounding environment S of the first route is ambient is 0, assuming the similarity threshold S t h res h old is 0.2, then the calculation in S2.4 shows that the first route and the second route are not similar.

[0075] Specifically, the method steps for the interest preference route prediction module 200 to bind the corresponding elevator with the corresponding route are as follows:

[0076] S200D, retrieve the monitoring screen of the monitoring equipment near the elevator;

[0077] S200E: Collect the number of consumers who move to route 1 after exiting the elevator C route1 and the number of moves to route 2 C route2 ;

[0078] S200F, set binding threshold B threshold , when moving to route 1, the number C route1 > Binding threshold B threshold When the elevator is bound to route 1, it will be bound to route 1. When it moves to route 2, the number C route2 > Binding threshold B threshoold , bind the elevator to route 2.

[0079] Specifically, during identification, suppose there are 20 consumers in elevator a. After these 20 consumers exit the elevator, 18 of them walk to route one, and 2 of them walk to route two. The binding threshold B threshoold The value is 80%. At this time, it is calculated that 90% of the consumers in elevator a will go to route 1 after exiting the elevator. At this time, route 1 is bound to elevator a. In this way, when consumers are guided to elevator a, most of them will go to route 1 after exiting the elevator, thereby achieving consumer diversion.

[0080] Furthermore, the method steps for the intelligent interaction guidance and diversion module 300 to establish a human-computer interaction control platform are as follows:

[0081] S300A. A human-machine interaction terminal is set at the entrance of the shopping mall. The human-machine interaction terminal includes at least one screen and a speaker. Consumers can input their destinations through the screen, and the human-machine interaction terminal can guide consumers to the corresponding elevator through the speaker.

[0082] S300B, cancel the control of the elevator by the control button, and establish a communication control connection with the elevator through the human-computer interaction terminal;

[0083] S300C, collecting the consumer's destination, obtaining route 1 and route 2 to the destination, and elevators corresponding to route 1 and route 2;

[0084] S300D, obtaining the physical condition information of the consumers, guiding all the consumers with a cold-sensitive constitution to the elevator corresponding to one of the routes in S300C, and guiding all the consumers with a heat-sensitive constitution to the elevator corresponding to another route in S300C;

[0085] S300E: When the consumer interacting with the human-computer interaction terminal enters the corresponding elevator, the elevator is controlled to rise to the floor corresponding to the destination;

[0086] refer to Figure 2 For example, if consumers a, b, and c are cold-sensitive, and consumers e, d, and f are heat-sensitive, and consumers a, b, c and e, d, and f all input destination a through the human-computer interaction terminal, then it means that consumers a, b, c and e, d, and f all need to go to destination a. Then, first obtain two routes to destination a, namely route one and route two, and then obtain the elevators corresponding to the two routes. Assuming that route one corresponds to elevator a and route two corresponds to elevator b, the human-computer interaction terminal can guide consumers a, b, and c to elevator a and consumers e, d, and f to elevator b. In this way, consumers a, b, and c go to destination a through route one after exiting elevator a, and consumers e, d, and f go to destination a through route two after exiting elevator b.

[0087] As a result, consumers a, b, c and consumers e, d, f are in different areas, and there are basically no consumers with different physiques in the corresponding areas. At this time, the cooling amount can be adjusted according to the positions of consumers a, b, c and consumers e, d, f.

[0088] S300F, setting a threshold for the number of people taking the elevator, when the number of consumers guided into the elevator is greater than the threshold for the number of people taking the elevator, controlling the elevator to rise to the floor corresponding to the destination;

[0089] S300G, set up an elevator reminder program to predict the time when the elevator will reach the threshold number of passengers based on the passenger flow, and notify consumers.

[0090] In this way, it is possible to achieve centralized guidance for consumers. For example, if the threshold for the number of people in the elevator is 20, the elevator will start only when the number of consumers in the elevator reaches 20. If the number of people does not reach 20, consumers can learn about the elevator running time through the elevator reminder program, and when the time arrives, consumers can go to the elevator to take the elevator.

[0091] S300H. When consumers corresponding to route one move to route two, the human-computer interaction terminal guides consumers with the same physique to the elevator corresponding to route two; when consumers corresponding to route two move to route one, the human-computer interaction terminal guides consumers with the same physique to the elevator corresponding to route one.

[0092] For example, when consumers a, b, and c who are afraid of cold walk into route two, the strong wind on route two is adjusted to weak wind. When consumers e, d, and f walk into route one, the weak wind on route one is adjusted to strong wind. At this time, the human-computer interaction terminal guides people who are afraid of cold to route two and people who are afraid of heat to route one, thereby improving the efficiency of guiding consumers.

[0093] Furthermore, the cooling capacity adjustment integrated management module 400 adjusts and manages the cooling capacity on two different routes in the following steps:

[0094] S400A, obtaining the route of the consumer with a cold-sensitive constitution, and adjusting the cold wind on the route to weak wind;

[0095] S400B, obtaining the route of the consumer with a heat-phobic constitution, and adjusting the cold wind on the route to strong wind;

[0096] S400C. Obtain the locations of consumers with a cold-sensitive constitution and consumers with a heat-sensitive constitution. When the consumers with a cold-sensitive constitution and consumers with a heat-sensitive constitution meet, adjust the weak wind on the original route to a strong wind, and adjust the strong wind on the original route to a weak wind.

[0097] For example, if consumers a, b, and c who are afraid of cold walk to destination a via route one, the cold wind in route one can be adjusted to weak wind, thereby reducing the amount of cold in route one; if consumers e, d, and f who are afraid of cold walk to destination a via route two, the cold wind in route two can be adjusted to strong wind, thereby avoiding overheating of consumers e, d, and f in route two.

[0098] At the same time, since Route 1 and Route 2 are different, consumers a, b, and c will go to Route 2 after finishing Route 1, and consumers e, d, and f who were originally on Route 2 will also go to Route 1. Therefore, after consumers a, b, c and consumers e, d, and f gather, the weak wind in Route 1 will be adjusted to strong wind, and the strong wind in Route 2 will be adjusted to weak wind.

[0099] It can be seen that reference Figure 3 Since the stores around the two routes are different, after consumers have visited the stores around the corresponding route, consumers with different physiques will be attracted to the other route, reducing the consumers' stay in the original route, thereby avoiding the phenomenon of large-scale mixing between consumers with different physiques and improving the feasibility of adjusting the cooling capacity.

[0100] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A refrigeration prediction management system based on big data analysis, characterized by: The system comprises an environmental adaptability recognition module (100), an interest preference route prediction module (200), an intelligent interactive guidance and diversion module (300), and a cooling capacity regulation integrated management module (400), wherein: The environmental adaptability identification module (100) collects consumers' sensitivity information to temperature, and identifies people with a cold-fearing constitution and people with a heat-fearing constitution based on the sensitivity information; The interest preference route prediction module (200) obtains two different routes for consumers to reach their desired destinations based on their behavioral habits, obtains the corresponding relationship between the two different routes and each elevator in the shopping mall, and binds the corresponding elevator to the corresponding route; The intelligent interactive guidance and diversion module (300) establishes a human-machine interactive control platform, collects information about the destination that consumers need to go to, and guides consumers with different physical conditions to elevators corresponding to different routes; The cooling capacity adjustment integrated management module (400) monitors the locations of consumers on two different routes in real time, and adjusts and manages the cooling capacity on the two different routes according to the consumers' physical information.

2. The refrigeration prediction management system based on big data analysis according to claim 1 is characterized in that: The method steps for the environmental adaptability recognition module (100) to recognize people with a cold-fearing physique and people with a heat-fearing physique are as follows: S100A, establish a cold-fear behavior database to record people's cold-fear posture information; S100B, establishing a communication connection with the monitoring equipment in the mall, and using the monitoring equipment to obtain image information inside the mall; S100C, monitoring the posture information of the consumer through the screen information, and when the posture information of the consumer is consistent with the posture information of fear of cold, marking the consumer as having a cold-fearing physique; when the posture information of the consumer is different from the posture information of fear of cold, marking the consumer as having a heat-fearing physique.

3. The refrigeration prediction management system based on big data analysis according to claim 1 is characterized in that: The method steps of the interest preference route prediction module (200) for obtaining two different routes are as follows: S200A, obtaining multiple routes for different consumers to enter the same store; S200B, randomly selecting two routes from the multiple routes, and calculating the similarity between the two routes; S200C: When the two routes are not similar, return to S200B; when the two routes are not similar, mark the two routes as route one and route two, respectively.

4. The refrigeration prediction management system based on big data analysis according to claim 3 is characterized in that: The method steps for calculating the similarity of two routes in S200B are as follows: S2.1, define two routes as the first route and the second route respectively; S2.

2. Obtain all environmental information around the first route F ambient ; S2.

3. Obtain the common environmental information S around the second route and the first route ambient ; S2.

4. Set similarity threshold S threshold , when the similarity threshold S threshold ≤ The environmental information S shared by the second route and the first route ambient / All environmental information around the first route F ambient When , it indicates that the first route is similar to the second route. When the similarity threshold S threshold > Environmental information S shared by the second route and the first route ambient / All environmental information around the first route F ambient , indicating that the first route and the second route are not similar.

5. The refrigeration prediction management system based on big data analysis according to claim 3 is characterized in that: The method steps of the interest preference route prediction module (200) for binding the corresponding elevator with the corresponding route are as follows: S200D, retrieve the monitoring screen of the monitoring equipment near the elevator; S200E: Collect the number of consumers who move to route 1 after exiting the elevator C route1 and the number of moves to route 2 C route2 ; S200F, set binding threshold B threshold , when moving to route 1, the number C route1 > Binding threshold B thrreshold When the elevator is bound to route 1, it will be bound to route 1. When it moves to route 2, the number C route2 > Binding threshold B threshold , bind the elevator to route 2.

6. The refrigeration prediction management system based on big data analysis according to claim 5 is characterized in that: The method steps of the intelligent interaction guiding diversion module (300) to establish a human-computer interaction control platform are as follows: S300A, set up a human-computer interaction terminal at the entrance of the shopping mall; S300B, cancel the control of the elevator by the control button, and establish a communication control connection with the elevator through the human-computer interaction terminal; S300C, collecting the consumer's destination, obtaining route 1 and route 2 to the destination, and elevators corresponding to route 1 and route 2; S300D, obtaining the physical condition information of the consumers, guiding all the consumers with a cold-sensitive constitution to the elevator corresponding to one of the routes in S300C, and guiding all the consumers with a heat-sensitive constitution to the elevator corresponding to another route in S300C; S300E: When the consumer interacting with the human-machine interaction terminal enters the corresponding elevator, the elevator is controlled to rise to the floor corresponding to the destination.

7. The refrigeration prediction management system based on big data analysis according to claim 6 is characterized in that: Also includes the following method steps: S300F, setting a threshold for the number of people taking the elevator, when the number of consumers guided into the elevator is greater than the threshold for the number of people taking the elevator, controlling the elevator to rise to the floor corresponding to the destination; S300G, set up an elevator reminder program to predict the time when the elevator will reach the threshold number of passengers based on the passenger flow, and notify consumers.

8. The refrigeration prediction management system based on big data analysis according to claim 6 is characterized in that: Also includes the following method steps: S300H. When consumers corresponding to route one move to route two, the human-computer interaction terminal guides consumers with the same physique to the elevator corresponding to route two; when consumers corresponding to route two move to route one, the human-computer interaction terminal guides consumers with the same physique to the elevator corresponding to route one.

9. The refrigeration prediction management system based on big data analysis according to claim 6, characterized in that: The method steps of the cooling capacity adjustment integrated management module (400) for adjusting and managing the cooling capacity on two different routes are as follows: S400A, obtaining the route of the consumer with a cold-sensitive constitution, and adjusting the cold wind on the route to weak wind; S400B, obtaining the route of the consumer with a heat-phobic constitution, and adjusting the cold wind on the route to strong wind; S400C. Obtain the locations of consumers with a cold-sensitive constitution and consumers with a heat-sensitive constitution. When the consumers with a cold-sensitive constitution and consumers with a heat-sensitive constitution meet, adjust the weak wind on the original route to a strong wind, and adjust the strong wind on the original route to a weak wind.

Images