An intelligent service method for production factor demand in industrial Internet environment

Abstract

The present invention discloses an intelligent service method for production factor demand in an industrial Internet environment, comprising: obtaining the spatial geographic location of all equipment in a region and converting it into a two-dimensional vector; dividing the equipment in the region by a hierarchical clustering method; all equipment is divided into different clusters, each cluster corresponding to an after-sales service area; determining the after-sales service area, and selecting the point with the lowest operation and maintenance cost in the area as the after-sales service point; the number of production factors configured for each after-sales service point is positively correlated with the number of equipment in the after-sales area connected to it; adopting a statistical strategy to obtain the probability of damage of equipment parts and components, as a basis for optimizing the inventory configuration of production factor parts and components; optimizing the configuration mode of parts and components in after-sales points according to the probability of parts damage and the enterprise's planning of redundancy; when the equipment density in the region changes significantly over time, re-execute the above steps to optimize the configuration mode of parts and components in the region.

Description

Technical Field

[0001] The present invention relates to an intelligent perception service method, and in particular to an intelligent service method oriented to production factor demand in an industrial Internet environment. Background Art

[0002] "Industrial Internet" is the key to building a comprehensive interconnection between people, machines and things in an industrial environment. It is based on the network, with the platform as the hub, data as the element and security as the guarantee. It is a new application model that deeply integrates the Internet, big data, artificial intelligence and other technologies with the industrial production field.

[0003] Taking the operation and maintenance of heavy machinery such as excavators as an example, when setting up after-sales points, traditional solutions are mainly based on empiricism. When choosing the location of after-sales points, companies usually choose locations with relatively low rents. When setting the number of after-sales points, companies usually set them according to the size of the city. In fact, urban development is not balanced. As time goes by, the number and scale of construction in different areas of the city will also vary greatly. How to dynamically and adaptively adjust the configuration of production factors in after-sales points according to the changes in the spatiotemporal location of urban construction points is a difficult point. Summary of the invention

[0004] Purpose of the invention: The technical problem to be solved by the present invention is to provide an intelligent service method for production factor needs in an industrial Internet environment in response to the shortcomings of the existing technology.

[0005] In order to solve the above technical problems, the present invention discloses an intelligent service method for production factor demand in an industrial Internet environment, comprising the following steps:

[0006] Step 1: The enterprise applies industrial Internet technology to obtain the spatial geographic location of all devices in the region and convert the location of the device in space into a two-dimensional vector;

[0007] Step 2: The density of devices in different areas is different. In order to ensure that the time for devices to receive after-sales service meets certain time constraints, hierarchical clustering is used to divide the devices in the area. After hierarchical clustering, all devices are divided into different clusters, and each cluster corresponds to an after-sales service area, thereby determining the after-sales service area.

[0008] Step 3: After determining the after-sales service area, select the point with the lowest operation and maintenance cost in the after-sales service area as the after-sales service point;

[0009] Step 4: The number of production factors configured at the after-sales service point is positively correlated with the number of equipment in the after-sales service area connected to the after-sales service point;

[0010] Step 5: Use statistical strategies to obtain the damage probability of each component in the equipment as the basis for optimizing the inventory configuration of components in the production factor; based on the obtained damage probability of components and the company's redundancy planning, optimize the configuration of components and the number of service personnel in the after-sales service point, thus completing the configuration of production factors;

[0011] Step 6: As time changes, the equipment density in different areas will also change. Whenever the equipment density in a region changes beyond the threshold, re-execute steps 1-5 to complete the production factor configuration again.

[0012] In step 1, in the industrial Internet environment, each piece of equipment shipped out of the factory will be tagged by the enterprise. After the equipment is sold, the location of each piece of equipment can be monitored by the enterprise internally, so the enterprise can obtain the location of all equipment in geographic space. Specifically, every time the user equipment arrives at a location, the equipment's tag data can be read by a nearby data reader and then transmitted to the enterprise's data center. After the enterprise collects the location information of all shipped equipment, it converts the spatial location of the equipment into a two-dimensional vector, which is used as data for cluster analysis.

[0013] In step 2 of the present invention, the method of using a hierarchical clustering method to determine the after-sales service area includes:

[0014] For device e k , whose position is represented by the two-dimensional vector z k =(a k1 ,a k2 ) indicates that, where a k1 Indicates longitude, a k2 Indicates latitude;

[0015] Two-dimensional vector z k and the two-dimensional vector z l The distance Dist(z k ,z l ) is calculated as:

[0016]

[0017] Among them, the two-dimensional vector z k Indicates device e k The position of the two-dimensional vector z l Indicates device e l The position of a kc Indicates z k The value of the cth dimension, a lc Indicates z l The value of the cth dimension of ;

[0018] At the beginning of the hierarchical clustering algorithm, each device is clustered separately; the two clusters closest to each other are merged until they cannot be merged. The merging methods include:

[0019] For a given cluster C x and cluster C y , the maximum distance d is calculated by max (C x ,C y ):

[0020]

[0021] Among them, z k ∈C x Indicates z k For the x The two-dimensional vector in z l ∈C y Indicates z l For the y The two-dimensional vector in ; During the hierarchical clustering process, the merging rules of two clusters include:

[0022] For a given distance constraint value dis, if the distance d between two clusters max (C x ,C y )>dis, the two clusters cannot be merged, otherwise the two clusters are merged; when the remaining clusters cannot be merged, the hierarchical clustering algorithm ends and the hierarchical clustering is completed;

[0023] A cluster after hierarchical clustering corresponds to a set of equipment served by an after-sales service point; after the hierarchical clustering is completed, the value of the number of equipment m served by each after-sales service point is the number of equipment in the cluster after hierarchical clustering.

[0024] In step 3 of the present invention, the method for determining the location of the after-sales service point includes:

[0025] Step 3-1, determining the area that meets the real-time constraint based on the cluster;

[0026] Step 3-2: In the area that meets the real-time constraint, the location of the after-sales point is determined by random sampling and taking the local optimal value.

[0027] The method for determining the area satisfying the real-time constraint according to the cluster in step 3-1 of the present invention includes:

[0028] Take the location of each device as the center of the circle, Draw a circle for the radius, and the area within the constraints of all devices is determined as the area that meets the real-time constraints.

[0029] The method for determining the location of the after-sales point in step 3-2 of the present invention includes:

[0030] Randomly search for a location as an alternative after-sales service point in an area that meets the real-time constraint; calculate the number of asset configurations when setting the alternative after-sales service point as the after-sales service point; and take the location with the lowest number of asset configurations as the location of the final after-sales service point.

[0031] In step 4, the number of parts and after-sales personnel configured in an after-sales point is positively correlated with the number of devices. However, due to differences between regions and between parts, the failure rates of the same device in different regions and the failure rates of different parts on the same device are different. It is unreasonable to simply configure the number of parts in proportion to the number of devices.

[0032] The method for optimizing the configuration of parts in the after-sales service point in step 5 of the present invention includes:

[0033] Step 5-1, based on historical statistical data, calculate the probability of failure of each part every day as the basic basis for the configuration of production factors;

[0034] Step 5-2, optimize the configuration of parts in after-sales service points according to the enterprise's redundancy planning;

[0035] Step 5-3, optimize the configuration of the number of service personnel in after-sales service points based on the company's redundancy planning.

[0036] The method for calculating the probability of failure of each component per day in step 5-1 of the present invention includes:

[0037] For a single after-sales service point, let the number of devices that need to be serviced be m, and the kth device uses e k = ... i The failure rate of each part is p i ; The expected number of failures per day for a part is calculated by i :

[0038] μ i =m·v i ·p i (3).

[0039] The method for redundancy planning according to the enterprise described in step 5-2 of the present invention includes:

[0040] According to the concept of binomial distribution, a variety of production factor configuration methods with real-time requirements are provided; assuming that whether a part fails is an independent event, for n parts, its distribution conforms to the binomial distribution; when the random variable X obeys the binomial distribution with parameters n and p, it is recorded as X~B(n,p). For a specific part i, the binomial distribution it obeys is X i ~B(m·v i ,p i ), which means that in m·v i The probability f(x) that x parts fail among all parts is:

[0041]

[0042] Enterprises configure production factors according to actual real-time requirements, where the degree of real-time is expressed by probability theory. The methods include:

[0043] Setting up an after-sales service point requires p l The probability of ensuring that all user requests are met within one day, then the i-th component configured at the after-sales service point must deploy at least x i , where x i The following inequality is satisfied:

[0044]

[0045] Finalize the quantity of each part configuration in each aftermarket location.

[0046] The method for optimizing the configuration of the number of service personnel in after-sales service points according to the enterprise's redundancy planning in step 5-3 of the present invention includes:

[0047] Based on statistical data, the company obtains the average time required for after-sales personnel to handle a fault. j , assuming that an after-sales point provides service for 8 hours a day, then the number of faults that each after-sales staff can handle per day is b num Use the following formula to calculate:

[0048]

[0049] Since different faults are independent of each other, the following formula is used to calculate the e of each device. k The probability of failure p k :

[0050]

[0051] The p k Substitute into formula (4) and formula (5) in step 5-2, and we get lWhen , the number of faulty devices that the after-sales service point has to deal with every day is x;

[0052] The enterprise determines the number of service personnel u required in each after-sales center by resolving the value of the number of devices x. num for:

[0053]

[0054] The method for completing the configuration of production factors again in step 6 of the present invention includes:

[0055] After configuring the initial number of production factors according to steps 1 to 5, count the number of devices served by the after-sales service point every day. If the number of devices served by the after-sales service point varies by more than 30% compared with the initial value, re-execute steps 1-5 to complete the production factor configuration again.

[0056] Beneficial effects:

[0057] When completing the configuration of production factors, the present invention can formulate a better production factor configuration plan based on the spatiotemporal location information of the equipment, effectively reducing the waste of human and material resources of the enterprise, while improving the experience of equipment users seeking after-sales service. The present invention is a product of the combination of advanced technologies such as industrial Internet and artificial intelligence, and is an advanced case of the combination of information technology and the service industry. Compared with the existing production factor configuration method of the enterprise, the present invention avoids the waste of resources caused by the production factor configuration method based on empiricism. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments, and the above and / or other advantages of the present invention will become more clear.

[0059] Figure 1 It is a schematic diagram of the production factor configuration process in the present invention.

[0060] Figure 2 It is a schematic diagram of the feasible domain for determining after-sales points in a cluster in the present invention. DETAILED DESCRIPTION

[0061] The present invention will be described in detail below in conjunction with the accompanying drawings. It should be noted that the described embodiments are only for the purpose of illustration and are not intended to limit the scope of the present invention.

[0062] The present invention discloses an intelligent service method for production factor demand in an industrial Internet environment. The method flow is as follows: Figure 1 As shown, the following steps are included.

[0063] In step 1, in the industrial Internet environment, each piece of equipment shipped out of the factory will be tagged by the enterprise. After the equipment is sold, the location of each piece of equipment can be monitored by the enterprise internally, so the enterprise can obtain the location of all equipment in geographic space. Specifically, every time the user equipment arrives at a location, the equipment's tag data can be read by a nearby data reader and then transmitted to the enterprise's data center. After the enterprise collects the location information of all shipped equipment, it converts the spatial location of the equipment into a two-dimensional vector, which is used as data for cluster analysis.

[0064] In step 2, the hierarchical clustering method is used to determine the number of after-sales points. First, the locations of all devices are abstracted into a two-dimensional plane. For a device e k , whose position can be represented by the two-dimensional vector z k =(a k1 ,a k2 ) indicates that, where a k1 Indicates longitude, a k2 The distance between any two vectors can be calculated using the following method.

[0065]

[0066] At the beginning of the hierarchical clustering algorithm, each device is clustered separately. Then, the two closest clusters are continuously merged until all clusters cannot be merged and the hierarchical clustering algorithm ends. Because each cluster is a set, the distance between two clusters needs to be represented here. For a given cluster C x and C y , the distance between two clusters can be calculated as follows:

[0067]

[0068] Formula (2) represents the cluster C x With cluster C y The maximum distance between them. Assuming that the speed at which after-sales personnel reach the location of the equipment is constant, and the distance between the after-sales point and the target point can be calculated using formula (1), the constraint of formula (2) can ensure that the maximum response time of the after-sales point when solving the maintenance task is within a certain time constraint range. For a given distance constraint value dis, if the distance d between the two clusters is max (C x ,C y )>dis, then the two clusters cannot be merged, otherwise the two clusters are merged; when the remaining clusters cannot be merged, the hierarchical clustering algorithm ends and the hierarchical clustering is completed. After the hierarchical clustering is completed, the value of the number of devices m served by each after-sales point is determined.

[0069] In step 3, after the cluster is determined, the location of the after-sales point needs to be determined. Considering that the cost of setting up an after-sales point in each location is different, the after-sales point should be set at the location with the lowest operation and maintenance cost. The cost of setting up an after-sales point mainly comes from two aspects: one is the rental of the after-sales point, and the other is the cost of the operation and maintenance personnel traveling back and forth between the target point and the after-sales point.

[0070] In order to determine the reasonable location of the after-sales point, the present invention first needs to determine the area that meets the real-time constraints based on the cluster. Figure 2 The example shown is used as an example. Figure 2 As shown in the figure, the black points represent the position of each device in the two-dimensional plane. The distance between the device and the after-sales point must be less than the distance constraint value. For a certain device, its location is the center of the circle and the radius is The inner area of ​​the circle is the feasible area that meets the real-time requirements. Figure 2 The middle area A is the area that meets the real-time requirements of four devices at the same time. The after-sales point should obviously be set within the scope of area A.

[0071] When determining the specific location of the after-sales point, the present invention determines the location of the after-sales point by random sampling and taking the local optimal value. In simple terms, multiple locations can be randomly found in area A as possible after-sales points, and then the number of asset allocations when setting the after-sales point at each point is calculated. The location with the lowest average daily asset allocation number is the location of the final after-sales point.

[0072] In step 4, the number of parts and after-sales personnel configured in an after-sales point is positively correlated with the number of devices. However, due to differences between regions and between parts, the failure rates of the same device in different regions and the failure rates of different parts on the same device are different. It is unreasonable to simply configure the number of parts in proportion to the number of devices.

[0073] In step 5, when configuring production factors, the impact of equipment failure rate on production factor configuration also needs to be considered. Obviously, the number of parts that are prone to failure should be increased in the after-sales point, while the number of parts that are not prone to failure should be appropriately reduced.

[0074] Based on the historical statistical data, the enterprise calculates the probability of failure of each part every day as the basic basis for the configuration of production factors. For a single after-sales point, assuming that the number of equipment to be serviced is m, and the kth equipment uses e k The configuration of production factors at the after-sales point is related to the number of equipment and the failure rate of each part on the equipment. Assume that a piece of equipment has a parts, and the i-th part has v iThe failure rate of each part is p i Then the expected number of failures of a part per day can be calculated as follows: i .

[0075] μ i =m·v i ·p i (3)

[0076] The configuration of production factors depends entirely on the expected value μ i In actual situations, the occurrence of failures has random fluctuations. In order to meet different real-time requirements, the configuration of production factors can be appropriately adjusted to improve the adaptability of the entire method.

[0077] The present invention introduces the concept of binomial distribution to design a production factor configuration method that can meet multiple real-time requirements. Assuming that whether a part fails is an independent event, for n parts, its distribution conforms to the binomial distribution. In general, the random variable X obeys the binomial distribution with parameters n and p, which we denote as X~B(n,p). For a specific part i, the binomial distribution it obeys is X i ~B(m·v i ,p i ), which means that in m·v i The probability f(x) that x parts fail among all parts is:

[0078]

[0079] Enterprises can provide different real-time production factor configuration methods according to actual conditions. The degree of real-time here can be expressed by probability theory. For example, if an enterprise wants to ensure that 90% of the time, an after-sales point can meet all maintenance requests within a day, then the real-time of this production factor configuration method can be regarded as 90%. Assuming that an after-sales point requires p l The probability of ensuring that all user requests can be satisfied within one day, then the i-th part configured at the after-sales point must be deployed at least x i , where x i The following inequality is satisfied:

[0080]

[0081] By using formulas (4) and (5), the quantity of each part that should be configured in the after-sales point can be determined.

[0082] In addition, companies can also rely on statistical data to obtain the average time b required for after-sales personnel to handle a fault. j, assuming that an after-sales point provides service for 8 hours a day, then the number of faults that each after-sales staff can handle per day is b num Use the following formula to calculate.

[0083]

[0084] Since different faults are independent of each other, the following formula can be used to calculate the e of each device k The probability of failure p k .

[0085]

[0086] The p k Substituting into formula (4) and formula (5), we can get l When the after-sales service point has to deal with the number of faulty equipment x every day

[0087] By resolving the value of x, the company can determine the number of service personnel u required in each after-sales center. num .

[0088]

[0089] Through formula (4) and (5), we can get the real-time requirement at p l When , the number of each type of parts should be configured. Assuming that the maintenance requests are independent of each other, the number of after-sales personnel that should be configured at each after-sales point can also be calculated using formulas (6)(7)(8).

[0090] In step 6, the location of the factory equipment will change greatly over time. For a single device, when its location changes significantly, it can choose to receive service from the nearest after-sales point. The movement of the equipment will cause changes in the way the means of production are configured in the after-sales point, so the enterprise needs to update the equipment set of an after-sales point server every day, and dynamically determine the number of means of production that should be configured in the after-sales point every day based on the scale of the number of service equipment at the after-sales point.

[0091] After a long period of adjustment, the strong real-time performance of the after-sales point cannot be guaranteed. As the number of construction projects in a place increases or decreases, the number of equipment may also change dramatically, so the utility of the after-sales point initially set up will be relatively reduced. In order to maximize the capacity of each after-sales point, if the number of equipment served by the after-sales service point changes by more than 30% compared with the initial value, re-execute steps 1-5 to complete the production factor configuration again.

[0092] In a specific implementation, the present application provides a computer storage medium and a corresponding data processing unit, wherein the computer storage medium can store a computer program, and the computer program can run the invention content of an intelligent service method for production factor demand in an industrial Internet environment provided by the present invention and some or all steps in each embodiment when executed by the data processing unit. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0093] Those skilled in the art can clearly understand that the technical solutions in the embodiments of the present invention can be implemented by means of computer programs and their corresponding general hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention can be essentially or partly contributed to the prior art in the form of a computer program, i.e., a software product, which can be stored in a storage medium and includes several instructions for enabling a device including a data processing unit (which can be a personal computer, a server, a single-chip microcomputer, a MUU or a network device, etc.) to execute the methods described in various embodiments of the present invention or certain parts of the embodiments.

[0094] The present invention provides an idea and method for an intelligent service method for production factor demand in an industrial Internet environment. There are many methods and ways to implement the technical solution. The above is only a preferred implementation of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention. All components not specified in this embodiment can be implemented using existing technologies.

Claims

1. An intelligent service method for production factor demand in the industrial Internet environment, It is characterized in that The following steps are involved: Step 1: The enterprise applies industrial Internet technology to obtain the spatial geographic location of all devices in the region and convert the location of the device in space into a two-dimensional vector; Step 2: Use hierarchical clustering to divide the devices in the area. After hierarchical clustering, all devices are divided into different clusters, each cluster corresponds to an after-sales service area, so as to determine the after-sales service area. Step 3: After determining the after-sales service area, select the point with the lowest operation and maintenance cost in the after-sales service area as the after-sales service point; Step 4: The number of production factors configured at the after-sales service point is positively correlated with the number of equipment in the after-sales service area connected to the after-sales service point; Step 5: Use statistical strategies to obtain the damage probability of each component in the equipment as the basis for optimizing the inventory configuration of components in the production factor; based on the obtained damage probability of components and the company's redundancy planning, optimize the configuration of components and the number of service personnel in the after-sales service point, thus completing the configuration of production factors; Step 6: When the equipment density in the area changes over time and exceeds the threshold, re-execute steps 1-5 to complete the production factor configuration again; In step 2, the method of using hierarchical clustering to determine the after-sales service area includes: For device e k , whose position is represented by the two-dimensional vector z k =(a k1 ,a k2 ) indicates that, where a k1 Indicates longitude, a k2 Indicates latitude; Two-dimensional vector z k and the two-dimensional vector z l The distance Dist(z k ,z l ) is calculated as: Among them, the two-dimensional vector z k Indicates device e k The position of the two-dimensional vector z l Indicates device e l The position of a kc Indicates z k The value of the cth dimension, a lc Indicates z l The value of the cth dimension of ; At the beginning of the hierarchical clustering algorithm, each device is clustered separately; the two clusters closest to each other are merged until they cannot be merged. The merging methods include: For a given cluster C x and cluster C y , the maximum distance d is calculated by max (C x ,C y ): Among them, z k ∈C x Indicates z k For the x The two-dimensional vector in z l ∈C y Indicates z l For the y The two-dimensional vector in ; During the hierarchical clustering process, the merging rules of two clusters include: For a given distance constraint value dis, if the distance d between two clusters max (C x ,C y )>dis, the two clusters cannot be merged, otherwise the two clusters are merged; when the remaining clusters cannot be merged, the hierarchical clustering algorithm ends and the hierarchical clustering is completed; A cluster after hierarchical clustering corresponds to a set of devices served by an after-sales service point; after the hierarchical clustering is completed, the value of the number of devices m served by each after-sales service point is the number of devices in the cluster after hierarchical clustering; In step 3, the method of selecting the point with the lowest operation and maintenance cost in the after-sales service area as the after-sales service point includes: Step 3-1, determining the area that meets the real-time constraint based on the cluster; Step 3-2, in the area that meets the real-time constraint, determine the location of the after-sales point by random sampling and taking the local optimal value; The method for optimizing the configuration of parts in the after-sales service point described in step 5 includes: Step 5-1, based on historical statistical data, calculate the probability of failure of each part every day as the basis for production factor configuration; Step 5-2, optimize the configuration of parts in after-sales service points according to the enterprise's redundancy planning; Step 5-3, optimize the configuration of the number of service personnel in after-sales service points according to the enterprise's redundancy planning; The method for optimizing the configuration of the number of service personnel in after-sales service points according to the enterprise's redundancy planning described in step 5-3 includes: Based on statistical data, the company obtains the average time required for after-sales personnel to handle a fault. j , assuming that an after-sales point provides service for 8 hours a day, then the number of faults handled by each after-sales staff per day is b num Use the following formula to calculate: Since different faults are independent of each other, the following formula is used to calculate the e of each device. k The probability of failure p k : The p k Substitute into the method of redundancy planning according to the enterprise described in step 5-2, and obtain l When , the number of faulty devices that the after-sales service point has to deal with every day is x; The enterprise then determines the number of service personnel u required in each after-sales center by resolving the value of the number of devices x. num for:

2. According to claim 1, an intelligent service method for production factor demand in an industrial Internet environment, It is characterized in that The method for determining the area satisfying the real-time constraint according to the cluster in step 3-1 includes: Take the location of each device as the center of the circle, Draw a circle for the radius, and the area within the constraints of all devices is determined as the area that meets the real-time constraints.

3. According to claim 2, an intelligent service method for production factor demand in an industrial Internet environment, It is characterized in that The method for determining the location of the after-sales point described in step 3-2 includes: Randomly search for a location as an alternative after-sales service point in an area that meets the real-time constraint; calculate the number of asset configurations when setting the alternative after-sales service point as the after-sales service point; and take the location with the lowest number of asset configurations as the location of the final after-sales service point.

4. According to claim 3, an intelligent service method for production factor demand in an industrial Internet environment, It is characterized in that The method described in step 5-1 for calculating the probability of failure of each part per day includes: For a single after-sales service point, let the number of devices that need to be serviced be m, and the kth device uses e k = ... i The failure rate of each part is p i ; The expected number of failures per day for a part is calculated by i : μ i =m·v i ·p i (3)。 5. According to claim 4, an intelligent service method for production factor demand in an industrial Internet environment, It is characterized in that The method for redundancy planning according to the enterprise described in step 5-2 includes: According to the concept of binomial distribution, a variety of production factor configuration methods with real-time requirements are provided; assuming that whether a part fails is an independent event, for n parts, its distribution conforms to the binomial distribution; when the random variable X obeys the binomial distribution with parameters n and p, it is recorded as X~B(n,p), and for part i, the binomial distribution is X i ~B(m·v i ,p i ), which means that in m·v i The probability f(x) that x parts fail among all parts is: Enterprises configure production factors according to actual real-time requirements, where the degree of real-time is expressed by probability theory. The methods include: Setting up an after-sales service point requires p l The probability of ensuring that all user requests are met within one day, then the i-th component configured at the after-sales service point must deploy at least x i , where x i The following inequality is satisfied: Finalize the quantity of each part configuration in each after-sales service point.

6. According to claim 5, an intelligent service method for production factor demand in an industrial Internet environment, It is characterized in that The method for completing the configuration of production factors again in step 6 includes: After configuring the initial number of production factors according to steps 1 to 5, count the number of devices served by the after-sales service point every day. If the number of devices served by the after-sales service point varies by more than 30% compared with the initial value, re-execute steps 1-5 to complete the production factor configuration again.

Images