Cigarette mixing state comprehensive evaluation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a smoke mixing state comprehensive evaluation method and device, electronic equipment and a storage medium. The method comprises the steps that the number of wrong cigarette cartons in each cigarette packet and respective position information of the wrong cigarette cartons in each cigarette packet are obtained; according to the number of the wrong cigarettes in each cigarette packet and the respective position information of the wrong cigarettes in each cigarette packet, multiple groups of first probabilities and multiple groups of second probabilities are determined, and the multiple groups of first probabilities are the respective probabilities, determined according to the number of the wrong cigarettes in each cigarette packet, of multiple cigarette mixing occurrence grades corresponding to each cigarette packet; the plurality of groups of second probabilities are respective probabilities of a plurality of cigarette mixing occurrence grades corresponding to each cigarette packet determined according to respective position information of the wrong cigarette cartons in each cigarette packet; and determining a final smoke mixing state according to the multiple groups of first probabilities and the multiple groups of second probabilities. According to the embodiment of the invention, the comprehensive evaluation method is used for determining whether the cigarette packet has cigarette mixing or not, false alarm is avoided, and automation and high precision of cigarette mixing detection are realized.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of logistics technology, and specifically to a method, device, electronic device and storage medium for comprehensive evaluation of smoke crosstalk status. Background Art

[0002] As demand for tobacco products continues to grow around the world, the tobacco industry is highly dependent on efficient and precise logistics systems.

[0003] The current cigarette packing process is that the cigarette cartons are transferred to the packaging equipment through the sorting line. The equipment will pack the cigarette cartons of the same order into a cigarette pack according to the order details, and then deliver these cigarette packs to the designated address. However, due to the lack of stability of most packaging equipment on the market, occasionally a cigarette carton will accidentally fall into the gap of the equipment, causing the packaged cigarette pack to not match the original order information.

[0004] Cigarette pack errors often occur in succession. When one pack goes wrong, the following packs will also go wrong, i.e., cross-packing occurs. This error is usually difficult to detect when the first pack goes wrong. When workers discover cross-packing, they need to find all the previous packs that went wrong from the stacked pallets and cages, which takes a lot of time and effort.

[0005] In order to reduce the workload of manually checking cigarette packs, an organization has developed an automated cross-smoke detection system that uses deep learning methods to identify the specifications of cigarette cartons, and then checks whether the specifications of the cigarette cartons exist in the cigarette pack order, and then checks and compares them in sequence to determine whether cross-smoke has occurred. However, due to various reasons such as the on-site environment, image quality, and the algorithm itself, the accuracy of deep learning methods in identifying cigarette cartons cannot reach 100%. As long as one cigarette in a cigarette pack is misidentified, cross-smoke false alarms will occur. Frequent false alarms will cause great trouble to workers who deal with cross-smoke errors. Summary of the invention

[0006] The embodiments of the present invention provide a comprehensive evaluation method, device, electronic device and storage medium for cross-smoke status, which are used to solve the problem that the accuracy of deep learning methods in identifying cigarette specifications cannot reach 100%. As long as one cigarette in a cigarette package is incorrectly identified as being of the wrong specification, cross-smoke false alarms will occur. Frequent false alarms will cause great trouble to workers who deal with cross-smoke errors.

[0007] In a first aspect, an embodiment of the present invention provides a method for comprehensively evaluating a smoke crosstalk state, comprising:

[0008] Obtain the number of erroneous cigarette strips in each cigarette pack and the respective position information of the erroneous cigarette strips in each cigarette pack;

[0009] According to the number of erroneous cigarettes in each cigarette pack and the respective position information of the erroneous cigarettes in each cigarette pack, a plurality of groups of first probabilities and a plurality of groups of second probabilities are determined, wherein the plurality of groups of first probabilities are the respective probabilities of the plurality of levels of cross-smoke occurrence corresponding to each cigarette pack determined according to the number of erroneous cigarettes in each cigarette pack, and the plurality of groups of second probabilities are the respective probabilities of the plurality of levels of cross-smoke occurrence corresponding to each cigarette pack determined according to the respective position information of the erroneous cigarettes in each cigarette pack;

[0010] The final smoke intermixing state is determined according to the multiple groups of first probabilities and the multiple groups of second probabilities.

[0011] In a possible implementation, determining multiple groups of first probabilities and multiple groups of second probabilities according to the number of erroneous cigarette strips in each cigarette pack and the respective position information of the erroneous cigarette strips in each cigarette pack includes:

[0012] Normalizing the number of erroneous cigarette strips in each cigarette pack and the respective position information of the erroneous cigarette strips in each cigarette pack;

[0013] According to the normalized value of the number of erroneous cigarette cartons, the normalized value of the position information of the erroneous cigarette cartons in the cigarette pack, and the three-level triangle membership function, multiple groups of first probabilities and multiple groups of second probabilities are determined.

[0014] In a possible implementation, normalizing the number of erroneous cigarette strips in each cigarette pack and the respective position information of the erroneous cigarette strips in each cigarette pack includes:

[0015] The normalized value of the number of error bars is:

[0016]

[0017] C i is the number of wrong cigarette cartons in the cigarette pack, C o is the total number of cigarettes in a pack, and i is the pack number;

[0018] The normalized value of the position information of the error cigarette in the cigarette pack is:

[0019]

[0020] When the error cigarette occurs in the first position, P j is the first preset threshold; when the error cigarette occurs at the second position, P j is the second preset threshold, and so on. When the error cigarette occurs at the Nth position, P j is the Nth preset threshold; N is the total number of wrong cigarettes in the cigarette pack, P j An important value used to indicate the position of the j-th erroneous cigarette in a cigarette pack.

[0021] In a possible implementation, the multiple smoke string occurrence levels include: a first smoke string occurrence level, a second smoke string occurrence level, and a third smoke string occurrence level, wherein the first smoke string occurrence level is used to indicate that smoke string has occurred, the second smoke string occurrence level is used to indicate suspected smoke string, and the third smoke string occurrence level is used to indicate that the cigarette pack is normal;

[0022] Determining multiple groups of first probabilities and multiple groups of second probabilities according to the normalized value of the number of erroneous cigarette strips, the normalized value of the position information of the erroneous cigarette strips in the cigarette pack, and the three-level triangle membership function includes:

[0023]

[0024] Where x can be the normalized value of the number of error bars x i 'Or the normalized value x of the position information of the error cigarette in the cigarette pack i ", μ1(x), μ2(x), μ3(x) represent multiple groups of first probabilities or multiple groups of second probabilities that the cross-smoke state of each cigarette pack belongs to the three states of "cross-smoke occurred", "suspected cross-smoke", and "normal cigarette pack" according to the number of erroneous cigarette cartons or the position information of the erroneous cigarette cartons in the cigarette pack, respectively. x1, x2, x3 are parameter thresholds respectively.

[0025] In a possible implementation, determining the final smoke intermixing state according to the multiple groups of first probabilities and the multiple groups of second probabilities includes:

[0026] Determine a primary evaluation vector according to the multiple groups of first probabilities and the multiple groups of second probabilities and their respective weights;

[0027] The final smoke intermixing state is determined according to the first-level judgment vector and the first-level weight matrix of the smoke intermixing state of each cigarette package.

[0028] In a possible implementation, determining a primary evaluation vector according to the multiple groups of first probabilities and the multiple groups of second probabilities and their respective weights includes:

[0029] The multiple groups of first probabilities and the multiple groups of second probabilities are denoted as R i ,

[0030]

[0031] i is the cigarette pack number, μ i11 (x)μ i21 (x)μ i31 (x) represents multiple groups of first probabilities, μ i12 (x)μ i22 (x)μ i32 (x) represents multiple sets of second probabilities;

[0032] The weights of multiple groups of first probabilities and multiple groups of second probabilities are recorded as A i ;

[0033] Determine the first-level judgment vector B i =A i ×R i , the first-level judgment vector is used to characterize the smoke-interference state of each cigarette pack.

[0034] In a possible implementation, determining the final smoke intermixing state according to the primary evaluation vector and the primary weight matrix of the smoke intermixing state of each cigarette package includes:

[0035] Determine the single factor evaluation matrix

[0036] The first-level weight matrix of each cigarette pack's smoking status is recorded as A;

[0037] Determine the secondary judgment vector B = A × R;

[0038] According to the secondary judgment vector, the final smoke leakage state is determined.

[0039] In a second aspect, an embodiment of the present invention provides a device for comprehensively evaluating a smoke crosstalk state, comprising:

[0040] An acquisition unit, used to acquire the number of erroneous cigarette strips in each cigarette pack and the respective position information of the erroneous cigarette strips in each cigarette pack;

[0041] A first determination unit is used to determine a plurality of groups of first probabilities and a plurality of groups of second probabilities according to the number of erroneous cigarettes in each cigarette pack and the respective position information of the erroneous cigarettes in each cigarette pack, wherein the plurality of groups of first probabilities are respective probabilities of a plurality of levels of cross-smoke occurrence corresponding to each cigarette pack determined according to the number of erroneous cigarettes in each cigarette pack, and the plurality of groups of second probabilities are respective probabilities of a plurality of levels of cross-smoke occurrence corresponding to each cigarette pack determined according to the respective position information of the erroneous cigarettes in each cigarette pack;

[0042] The second determining unit is used to determine a final smoke intermixing state according to the multiple groups of first probabilities and the multiple groups of second probabilities.

[0043] In a third aspect, an embodiment of the present invention provides an electronic device, including:

[0044] A memory and a processor, wherein the processor and the memory communicate with each other via a bus; the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the method described in the first aspect and each step in various possible implementations.

[0045] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect and each step in various possible implementations.

[0046] In a fifth aspect, an embodiment of the present invention provides a computer program product comprising instructions, and when the computer program product is run on a computer, each step in the method described in the first aspect and its various possible implementations is executed by the computer.

[0047] The embodiments of the present invention disclose the following technical effects:

[0048] A comprehensive evaluation method is used to determine whether cross-smoke has occurred in a cigarette pack, thereby avoiding false alarms and achieving automation and high precision of cross-smoke detection.

[0049] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 A system architecture diagram applicable to the embodiment of the present invention;

[0052] Figure 2 A schematic diagram of a flow chart of a comprehensive evaluation method for smoke crosstalk status provided by an embodiment of the present invention;

[0053] Figure 3 A schematic diagram of the structure of a comprehensive evaluation model when N=3 provided in an embodiment of the present invention;

[0054] Figure 4 A schematic diagram of the number of erroneous cigarette cartons in each cigarette pack and the positions of the erroneous cigarette cartons in the cigarette pack provided by an embodiment of the present invention;

[0055] Figure 5 A schematic diagram of a very important position, a less important position and an unimportant position in a cigarette pack provided by an embodiment of the present invention;

[0056] Figure 6 A schematic diagram of a three-level triangle membership function provided by an embodiment of the present invention;

[0057] Figure 7 A schematic block diagram of a comprehensive evaluation device for smoke crosstalk status provided by an embodiment of the present invention;

[0058] Figure 8 A schematic block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0060] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0061] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0062] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if determining" or "if monitoring (stated condition or event)" may be interpreted as "when determining" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0063] Cigarette pack errors often occur in succession. When one pack goes wrong, the following packs will also go wrong, i.e., cross-packing occurs. This error is usually difficult to detect when the first pack goes wrong. When workers discover cross-packing, they need to find all the previous packs that went wrong from the stacked pallets and cages, which takes a lot of time and effort.

[0064] In order to reduce the workload of manually checking cigarette packs, an organization has developed an automated cross-smoke detection system that uses deep learning methods to identify the specifications of cigarette cartons, and then checks whether the specifications of the cigarette cartons exist in the cigarette pack order, and then checks and compares them in sequence to determine whether cross-smoke has occurred. However, due to various reasons such as the on-site environment, image quality, and the algorithm itself, the accuracy of deep learning methods in identifying cigarette cartons cannot reach 100%. As long as one cigarette in a cigarette pack is misidentified, cross-smoke false alarms will occur. Frequent false alarms will cause great trouble to workers who deal with cross-smoke errors.

[0065] In view of this, the embodiment of the present invention provides a new idea. In order to facilitate the understanding of the present application, the system architecture based on the embodiment of the present invention is first described. Figure 1 An exemplary system architecture to which the present invention can be applied is shown. Figure 1 As shown in , the system architecture may include a terminal device and a comprehensive smoke crosstalk status evaluation device located at the server end.

[0066] The terminal devices may include, but are not limited to, smart mobile terminals, smart home devices, wearable devices, PCs (Personal Computers), etc. Smart mobile terminals may include mobile phones, tablet computers, laptop computers, PDAs (Personal Digital Assistants), Internet cars, etc. Smart home devices may include smart TVs, smart refrigerators, etc. Wearable devices may include smart watches, smart glasses, virtual reality devices, augmented reality devices, mixed reality devices (i.e., devices that can support virtual reality and augmented reality), etc.

[0067] The smoke crosstalk status comprehensive evaluation device may use the smoke crosstalk status comprehensive evaluation method provided in the embodiment of the present invention to perform comprehensive evaluation of the smoke crosstalk status.

[0068] The above-mentioned smoke crosstalk status comprehensive evaluation device can be set in a single server, a server group consisting of multiple servers, or a cloud server. A cloud server, also known as a cloud computing server or cloud host, is a host product in the cloud computing service system to solve the defects of difficult management and weak service scalability in traditional physical hosts and virtual private servers (VPS). Figure 1 In addition to the shown architecture, the smoke crosstalk status comprehensive evaluation device can also be set on a computer terminal with strong computing power.

[0069] Figure 2 A schematic diagram of a flow chart of a comprehensive evaluation method for smoke crosstalk status provided by an embodiment of the present invention. The method can be performed by Figure 1The smoke cross-talk status comprehensive evaluation device in the system shown is executed. Figure 2 As shown in , the method may include the following steps:

[0070] Step 201: Obtain the number of erroneous cigarette strips in each cigarette pack and the respective position information of the erroneous cigarette strips in each cigarette pack.

[0071] Step 202: Determine multiple groups of first probabilities and multiple groups of second probabilities based on the number of erroneous cigarette rods in each cigarette pack and the respective position information of the erroneous cigarette rods in each cigarette pack. The multiple groups of first probabilities are the respective probabilities of multiple levels of cross-cigarette occurrence corresponding to each cigarette pack determined based on the number of erroneous cigarette rods in each cigarette pack, and the multiple groups of second probabilities are the respective probabilities of multiple levels of cross-cigarette occurrence corresponding to each cigarette pack determined based on the respective position information of the erroneous cigarette rods in each cigarette pack.

[0072] Step 203: Determine the final smoke contamination state according to the multiple groups of first probabilities and the multiple groups of second probabilities.

[0073] The following is a detailed description of each step in the above process and the effects that can be further produced in conjunction with the embodiments of the present invention. It should be noted that the limitations such as "first" and "second" involved in the embodiments of the present invention do not have limitations in terms of size, order, and quantity, and are only used to distinguish them in name, for example, "first probability" and "second probability" are used to distinguish two different probabilities.

[0074] First, the above step 201, namely, "obtaining the number of erroneous cigarette strips in each cigarette pack and the respective position information of the erroneous cigarette strips in each cigarette pack" is described in detail in conjunction with the embodiment of the present invention.

[0075] In an embodiment of the present invention, each target image is obtained, and the target image is an image of a cigarette pack. The specification information of the cigarette carton at each position in each target image is identified based on a deep learning algorithm. The specification information of the cigarette carton at each position in each target image is compared with the preset specification information of the cigarette carton at each position in each cigarette pack, and the number of erroneous cigarette carton in the image of each cigarette pack and the respective position information of the erroneous cigarette carton in each cigarette pack are determined.

[0076] In an embodiment of the present invention, a comprehensive evaluation model is established to determine the evaluation indicators. The model structure includes three levels: a target layer, an indicator layer, and a sub-indicator layer. The target layer is the evaluation of the smoke-smoke status of the sorting line. The indicator layer includes the smoke-smoke status of the first cigarette pack, the smoke-smoke status of the second cigarette pack, ..., the smoke-smoke status of the Nth cigarette pack. The sub-indicator layer includes two indicators: the number of erroneous cigarette cartons and the position information of the erroneous cigarette cartons in the cigarette pack. N is an integer greater than or equal to 2. Exemplarily, in an embodiment of the present invention, when N=3, the model structure is as follows: Figure 3 See Figure 3, the number of wrong cigarettes in the sub-index layer is the number of wrong cigarette strips, and the wrong cigarette position is the position information of the wrong cigarette strips in the cigarette pack. Cigarette pack 1, cigarette pack 2, and cigarette pack 3 in the index layer are the first cigarette pack cross-contamination status, the second cigarette pack cross-contamination status, and the third cigarette pack cross-contamination status respectively. The comprehensive evaluation of the cross-contamination status of the sorting line in the target layer is the final cross-contamination status.

[0077] In the embodiment of the present invention, it is assumed that there are three cigarette packs. Figure 4 As shown, there is no error cigarette in the first cigarette pack, one error cigarette in the second cigarette pack, and two error cigarettes in the third cigarette pack, and the position information of the error cigarettes in each cigarette pack is as follows Figure 4 shown.

[0078] The above step 202, i.e., "determining multiple groups of first probabilities and multiple groups of second probabilities based on the number of erroneous cigarettes in each cigarette pack and the respective position information of the erroneous cigarettes in each cigarette pack, wherein the multiple groups of first probabilities are the respective probabilities of multiple levels of cross-cigarette occurrence corresponding to each cigarette pack determined according to the number of erroneous cigarettes in each cigarette pack, and the multiple groups of second probabilities are the respective probabilities of multiple levels of cross-cigarette occurrence corresponding to each cigarette pack determined according to the respective position information of the erroneous cigarettes in each cigarette pack" is described in detail below in conjunction with an embodiment of the present invention.

[0079] In the embodiment of the present invention, multiple levels of cross-smoke occurrence include: a first level of cross-smoke occurrence, a second level of cross-smoke occurrence, and a third level of cross-smoke occurrence. The first level of cross-smoke occurrence is used to indicate that cross-smoke has occurred, the second level of cross-smoke occurrence is used to indicate suspected cross-smoke, and the third level of cross-smoke occurrence is used to indicate that the cigarette pack is normal, that is, V = {cross-smoke occurrence (n1), suspected cross-smoke (n2), normal cigarette pack (n3)}. "Cigarette cross-smoke occurrence" means that the sorting line has determined that cross-smoke has occurred, and the staff needs to handle it in time; "suspected cross-smoke" means that there may be a situation in the cigarette packs of the sorting line that the detected cigarette specifications do not match the order, but it has not occurred continuously and does not need to be handled temporarily; "normal cigarette pack" means that the cigarette pack status of the sorting line is normal.

[0080] In the embodiment of the present invention, the number of erroneous cigarettes in each cigarette pack and the respective position information of the erroneous cigarettes in each cigarette pack are normalized respectively, and the value of the normalized number of erroneous cigarettes is:

[0081]

[0082] C i is the number of wrong cigarette cartons in the cigarette pack, C o is the total number of cigarette cartons in a cigarette pack, and i is the serial number of the cigarette pack. In the embodiment of the present invention, the number of cigarette packs is 3. When i=1, the normalized value of the number of erroneous cigarette cartons in the first cigarette pack is x1'=x 11=1-(0 / 35)=1. When i=2, the normalized value of the number of erroneous cigarettes in the second cigarette pack is x2'=x 21 =1-(1 / 15)=14 / 15. When i=3, the normalized value of the number of erroneous cigarettes in the third cigarette pack is x3'=x 31 =1-(2 / 20)=9 / 10.

[0083] The normalized value of the position information of the error cigarette in the cigarette pack is:

[0084]

[0085] When the error cigarette occurs in the first position, P j is the first preset threshold; when the error cigarette occurs at the second position, P j is the second preset threshold, and so on. When the error cigarette occurs at the Nth position, P j is the Nth preset threshold; N is the total number of wrong cigarettes in the cigarette pack, P j It is used to indicate the importance value of the position of the jth wrong cigarette in the cigarette pack, where j is the serial number of the wrong cigarette in the cigarette pack. In the embodiment of the present invention, N=3, the first preset threshold is 1, the second preset threshold is 0.6, and the third preset threshold is 0.2. The first position is the most important position, which refers to the four corners of the cigarette pack, namely Figure 5 The second position is the second most important position, which refers to the first and last columns of the cigarette pack (excluding the four corners of the cigarette pack), that is, Figure 5 The third position is an unimportant position, which refers to the position other than the first and last column in the cigarette pack, i.e. Figure 5 In the embodiment of the present invention, when i=1, the value of the position information of the wrong cigarette in the first cigarette pack is x1″=x 12 = 1. When i = 2, the value of the position information of the wrong cigarette in the second cigarette pack is x1" = x 22 =1-(0.6 / 1)=0.4. When i=3, the value of the position information of the erroneous cigarette in the third cigarette pack is x1″=x 32 =1-[(0.6+0.2) / 2)=0.6.

[0086] In the embodiment of the present invention, according to the normalized value of the number of erroneous cigarette cartons, the normalized value of the position information of the erroneous cigarette cartons in the cigarette pack, and the three-level triangle membership function (such as Figure 6 As shown), multiple groups of first probabilities and multiple groups of second probabilities are determined. Specifically,

[0087]

[0088] Where x can be the normalized value of the number of error bars x i'Or the normalized value x of the position information of the error cigarette in the cigarette pack i ", μ1(x), μ2(x), μ3(x) respectively represent multiple groups of first probabilities or multiple groups of second probabilities that the cross-smoke state of each cigarette package belongs to the three states of "cross-smoke occurred", "suspected cross-smoke", and "normal cigarette package" according to the number of erroneous cigarettes or the position information of the erroneous cigarettes in the cigarette package, and x1, x2, and x3 are parameter thresholds respectively. That is to say, the embodiment of the present invention can determine the degree of membership of the cross-smoke state of each cigarette package to the three states of "cross-smoke occurred", "suspected cross-smoke", and "normal cigarette package" according to the two sub-indicators of the number of erroneous cigarettes or the position information of the erroneous cigarettes in the cigarette package. In the embodiment of the present invention, the parameter thresholds x1, x2, and x3 are shown in Table 1.

[0089] Table 1

[0090]

[0091] It should be noted that a set of first probabilities is the respective probabilities of multiple smoke intermixing levels corresponding to a cigarette pack, and a set of second probabilities is the respective probabilities of multiple smoke intermixing levels corresponding to the cigarette pack determined according to the respective position information of the erroneous cigarette strips in the current cigarette pack.

[0092] The above step 203, namely "determining the final smoke intermixing state according to the multiple groups of first probabilities and the multiple groups of second probabilities", is described in detail below in conjunction with an embodiment of the present invention.

[0093] In the embodiment of the present invention, a first-level judgment vector is determined based on multiple groups of first probabilities and multiple groups of second probabilities and their respective weights. The first-level judgment vector is used to characterize the smoke-crossing state of each cigarette package.

[0094] As a possible implementation method, first, multiple groups of first probabilities and multiple groups of second probabilities are recorded as R i ,

[0095]

[0096] i is the cigarette pack number, μ i11 (x)μ i21 (x)μ i31 (x) represents multiple groups of first probabilities, μ i12 (x)μ i22 (x)μ i32 (x) represents multiple sets of second probabilities.

[0097] The x calculated in step 202 is 11 、x 21 、x 31 、x 12 、x 22 、x 32Substitute into formulas (1), (2) and (3) respectively. In the embodiment of the present invention, when i=1, the first group of first probabilities are μ 111 (x) = μ1(x) = 0, μ 121 (x) = μ2(x) = 0, μ 131 (x)=μ3(x=1, the second probability of the first group is μ 112 (x) = μ1(x) = 0, μ 122 (x) = μ2(x) = 0, μ 132 (x) = μ3(x) = 1. When i = 2, the first probabilities of the second group are μ 211 (x) = μ1(x) = 0, μ 221 (x) = μ2(x) = 0, μ 231 (x)=μ3(x=1, the second group of second probabilities are μ 212 (x)=μ1(x)=(0.5-0.4) / (0.5-0.2)=1 / 3,μ 222 (x)=μ2(x)=(0.4-0.2) / (0.5-0.2)=2 / 3,μ 232 (x) = μ3(x) = 0. When i = 3, the first probabilities of the third group are μ 311 (x) = μ1(x) = 0, μ 321 (x) = μ2(x) = 0, μ 331 (x)=μ3(x=1, the second probabilities of the third group are μ 312 (x) = μ1(x) = 0, μ 322 (x)=μ2(x)=(0.8-0.6) / (0.8-0.5)=2 / 3,μ 332 (x)=μ3(x)=(0.6-0.5) / (0.5-0.2)=1 / 3.

[0098] therefore,

[0099] Then, the weights of the multiple groups of first probabilities and the multiple groups of second probabilities are recorded as A i ; Among them, A1=[a 11 ,a 12 ],A2=[a 21 ,a 22 ], ...A i =[a i1 ,a i2 In the embodiment of the present invention, it is assumed that A1=A2=A3=[0.5 0.5].

[0100] Finally, determine the first-level judgment vector B i =A i ×Ri . Where, when i=1,

[0101] In the embodiment of the present invention, the final smoke intermixing state is determined based on the primary evaluation vector and the primary weight matrix of the smoke intermixing state of each cigarette package.

[0102] As a possible implementation method, first, determine the single factor evaluation matrix In an embodiment of the present invention,

[0103] Then, the first-level weight matrix of each cigarette pack's smoke-binding state is recorded as A; where A=[a1,a2,...,a i In the embodiment of the present invention, A=[0.3 0.3 0.4]

[0104] Finally, the secondary evaluation vector B=A×R is determined. In the embodiment of the present invention,

[0105]

[0106] According to the secondary judgment vector, the final smoke-smoke status is determined. In other words, according to the maximum membership principle, the smoke-smoke occurrence level corresponding to the maximum element in the secondary judgment vector is determined as the final smoke-smoke status, and the final smoke-smoke status of the sorting line can be determined as "smoke-smoke occurs", "smoke-smoke suspected", or "cigarette package is normal". Since 43 / 60 is the largest in B, according to the maximum membership principle, the final smoke-smoke status is "cigarette package is normal".

[0107] It can be seen from the above content that the embodiment of the present invention determines whether smoke cross-talk occurs in a cigarette pack through a comprehensive evaluation method, avoids false alarms, and realizes automation and high precision of smoke cross-talk detection.

[0108] According to an embodiment of another aspect, a device for comprehensively evaluating smoke cross-talk status is provided. Figure 7 A schematic block diagram of a comprehensive evaluation device for smoke leakage status according to an embodiment is shown. The device can be arranged at Figure 1 The server side of the architecture shown in Figure 1. Figure 7 As shown, the device 700 may include: an acquisition unit 701, a first determination unit 702, and a second determination unit 703. The main functions of each component unit are as follows:

[0109] The acquisition unit 701 is used to acquire the number of erroneous cigarette strips in each cigarette pack and the respective position information of the erroneous cigarette strips in each cigarette pack;

[0110] The first determination unit 702 is used to determine multiple groups of first probabilities and multiple groups of second probabilities according to the number of erroneous cigarettes in each cigarette pack and the respective position information of the erroneous cigarettes in each cigarette pack, wherein the multiple groups of first probabilities are the respective probabilities of multiple levels of cross-smoke occurrence corresponding to each cigarette pack determined according to the number of erroneous cigarettes in each cigarette pack, and the multiple groups of second probabilities are the respective probabilities of multiple levels of cross-smoke occurrence corresponding to each cigarette pack determined according to the respective position information of the erroneous cigarettes in each cigarette pack;

[0111] The second determination unit 703 is used to determine the final smoke intermixing state according to the multiple groups of first probabilities and the multiple groups of second probabilities.

[0112] In a possible implementation, the first determining unit 702 includes a normalization unit and a third determining unit;

[0113] The normalization unit is used to normalize the number of erroneous cigarette cartons in each cigarette pack and the respective position information of the erroneous cigarette cartons in each cigarette pack;

[0114] The third determination unit is used to determine multiple groups of first probabilities and multiple groups of second probabilities according to the normalized value of the number of erroneous cigarette cartons, the normalized value of the position information of the erroneous cigarette cartons in the cigarette pack, and the three-level triangle membership function.

[0115] In a possible implementation, the normalization unit is specifically used to:

[0116] The normalized value of the number of error bars is:

[0117]

[0118] C i is the number of wrong cigarette cartons in the cigarette pack, C o is the total number of cigarettes in a pack, and i is the pack number;

[0119] The normalized value of the position information of the error cigarette in the cigarette pack is:

[0120]

[0121] When the error cigarette occurs in the first position, P j is the first preset threshold; when the error cigarette occurs at the second position, P j is the second preset threshold, and so on. When the error cigarette occurs at the Nth position, P j is the Nth preset threshold; N is the total number of wrong cigarettes in the cigarette pack, P j An important value used to indicate the position of the j-th erroneous cigarette in a cigarette pack.

[0122] In a possible implementation, the multiple smoke string occurrence levels include: a first smoke string occurrence level, a second smoke string occurrence level, and a third smoke string occurrence level, wherein the first smoke string occurrence level is used to indicate that smoke string has occurred, the second smoke string occurrence level is used to indicate suspected smoke string, and the third smoke string occurrence level is used to indicate that the cigarette pack is normal;

[0123] The third determining unit is specifically configured to:

[0124]

[0125] Where x can be the normalized value of the number of error bars x i 'Or the normalized value x of the position information of the error cigarette in the cigarette pack i ", μ1(x), μ2(x), μ3(x) represent multiple groups of first probabilities or multiple groups of second probabilities that the cross-smoke state of each cigarette pack belongs to the three states of "cross-smoke occurred", "suspected cross-smoke", and "normal cigarette pack" according to the number of erroneous cigarette cartons or the position information of the erroneous cigarette cartons in the cigarette pack, respectively. x1, x2, x3 are parameter thresholds respectively.

[0126] In a possible implementation, the second determining unit 703 includes a fourth determining unit and a fifth determining unit;

[0127] The fourth determining unit is used to determine a primary evaluation vector according to the multiple groups of first probabilities and the multiple groups of second probabilities and their respective weights;

[0128] The fifth determination unit is used to determine the final smoke intermixing state according to the first-level evaluation vector and the first-level weight matrix of the smoke intermixing state of each cigarette package.

[0129] In a possible implementation, the fourth determining unit is specifically configured to:

[0130] The multiple groups of first probabilities and the multiple groups of second probabilities are denoted as R i ,

[0131]

[0132] i is the cigarette pack number, μ i11 (x)μ i21 (x)μ i31 (x) represents multiple groups of first probabilities, μ i12 (x)μ i22 (x)μ i32 (x) represents multiple sets of second probabilities;

[0133] The weights of multiple groups of first probabilities and multiple groups of second probabilities are recorded as A i ;

[0134] Determine the first-level judgment vector Bi =A i ×R i , the first-level judgment vector is used to characterize the smoke-interference state of each cigarette pack.

[0135] In a possible implementation, the fifth determining unit is specifically configured to:

[0136] Determine the single factor evaluation matrix

[0137] The first-level weight matrix of each cigarette pack's smoking status is recorded as A;

[0138] Determine the secondary judgment vector B = A × R;

[0139] According to the secondary judgment vector, the final smoke leakage state is determined.

[0140] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0141] In addition, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of any one of the methods in the aforementioned method embodiments are implemented.

[0142] And an electronic device, comprising:

[0143] one or more processors; and

[0144] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method described in any one of the aforementioned method embodiments.

[0145] An embodiment of the present invention further provides a computer program product, including a computer program, which implements the steps of any one of the methods in the aforementioned method embodiments when executed by a processor.

[0146] in, Figure 8 The architecture of the electronic device is exemplarily shown, which may include a processor 810, a video display adapter 811, a disk drive 812, an input / output interface 813, a network interface 814, and a memory 820. The processor 810, the video display adapter 811, the disk drive 812, the input / output interface 813, the network interface 814, and the memory 820 may be communicatively connected via a communication bus 830.

[0147] The processor 810 may be implemented by a general-purpose CPU, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present invention.

[0148] The memory 820 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 820 can store an operating system 821 for controlling the operation of the electronic device 800, and a basic input and output system (BIOS) 822 for controlling the low-level operation of the electronic device 800. In addition, a web browser 823, a data storage management system 824, and a comprehensive evaluation device for cross-smoke status 825, etc. can also be stored. The comprehensive evaluation device for cross-smoke status 825 can be an application program for specifically implementing the operations of the aforementioned steps in the embodiment of the present invention. In short, when the technical solution provided by the embodiment of the present invention is implemented by software or firmware, the relevant program code is stored in the memory 820 and is called and executed by the processor 810.

[0149] The input / output interface 813 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0150] The network interface 814 is used to connect to a communication module (not shown) to achieve communication interaction between the device and other devices. The communication module can achieve communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0151] The bus 830 comprises a pathway for transmitting information between the various components of the device (eg, the processor 810, the video display adapter 811, the disk drive 812, the input / output interface 813, the network interface 814, and the memory 820).

[0152] It should be noted that, although the above device only shows a processor 810, a video display adapter 811, a disk drive 812, an input / output interface 813, a network interface 814, a memory 820, a bus 830, etc., in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include components necessary for implementing the solution of the present application, and does not necessarily include all the components shown in the figure.

[0153] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0154] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, rather than to limit them. Although the embodiments of the present invention have been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A comprehensive evaluation method for smoke leakage status, characterized in that: include: Obtain the number of erroneous cigarette strips in each cigarette pack and the respective position information of the erroneous cigarette strips in each cigarette pack; According to the number of erroneous cigarettes in each cigarette pack and the respective position information of the erroneous cigarettes in each cigarette pack, a plurality of groups of first probabilities and a plurality of groups of second probabilities are determined, wherein the plurality of groups of first probabilities are the respective probabilities of the plurality of levels of cross-smoke occurrence corresponding to each cigarette pack determined according to the number of erroneous cigarettes in each cigarette pack, and the plurality of groups of second probabilities are the respective probabilities of the plurality of levels of cross-smoke occurrence corresponding to each cigarette pack determined according to the respective position information of the erroneous cigarettes in each cigarette pack; The final smoke intermixing state is determined according to the multiple groups of first probabilities and the multiple groups of second probabilities.

2. The method according to claim 1, characterized in that: Determining multiple groups of first probabilities and multiple groups of second probabilities according to the number of erroneous cigarette strips in each cigarette pack and the respective position information of the erroneous cigarette strips in each cigarette pack includes: Normalizing the number of erroneous cigarette strips in each cigarette pack and the respective position information of the erroneous cigarette strips in each cigarette pack; According to the normalized value of the number of erroneous cigarette cartons, the normalized value of the position information of the erroneous cigarette cartons in the cigarette pack, and the three-level triangle membership function, multiple groups of first probabilities and multiple groups of second probabilities are determined.

3. The method according to claim 2, characterized in that The normalizing of the number of erroneous cigarette strips in each cigarette pack and the respective position information of the erroneous cigarette strips in each cigarette pack comprises: The normalized value of the number of error bars is: C i is the number of wrong cigarette cartons in the cigarette pack, C o is the total number of cigarettes in a pack, and i is the pack number; The normalized value of the position information of the error cigarette in the cigarette pack is: When the error cigarette occurs in the first position, P j is the first preset threshold; when the error cigarette occurs at the second position, P j is the second preset threshold, and so on. When the error cigarette occurs at the Nth position, P j is the Nth preset threshold; N is the total number of wrong cigarettes in the cigarette pack, P j An important value used to indicate the position of the j-th erroneous cigarette in a cigarette pack.

4. The method according to claim 3, characterized in that The multiple smoke string occurrence levels include: a first smoke string occurrence level, a second smoke string occurrence level, and a third smoke string occurrence level, wherein the first smoke string occurrence level is used to indicate that smoke string has occurred, the second smoke string occurrence level is used to indicate suspected smoke string, and the third smoke string occurrence level is used to indicate that the cigarette pack is normal; The method of determining multiple groups of first probabilities and multiple groups of second probabilities according to the normalized value of the number of erroneous cigarette strips, the normalized value of the position information of the erroneous cigarette strips in the cigarette pack, and the three-level triangle membership function includes: Where x can be the normalized value of the number of error bars x i 'Or the normalized value x of the position information of the error cigarette in the cigarette pack i ", μ1(x), μ2(x), μ3(x) represent the multiple groups of first probabilities or multiple groups of second probabilities of each cigarette pack belonging to the three states of "smoke cross-talk occurred", "smoke cross-talk suspected", and "normal cigarette pack" according to the number of erroneous cigarette cartons or the position information of the erroneous cigarette cartons in the cigarette pack, respectively. x1, x2, x3 are the parameter thresholds respectively.

5. The method according to any one of claims 1 to 4, characterized in that: The determining of the final smoke intermixing state according to the multiple groups of first probabilities and the multiple groups of second probabilities includes: Determine a primary evaluation vector according to the multiple groups of first probabilities and the multiple groups of second probabilities and their respective weights; The final smoke intermixing state is determined according to the first-level judgment vector and the first-level weight matrix of the smoke intermixing state of each cigarette package.

6. The method according to claim 5, characterized in that The step of determining a primary evaluation vector according to the plurality of groups of first probabilities and the plurality of groups of second probabilities and their respective weights includes: The multiple groups of first probabilities and the multiple groups of second probabilities are denoted as R i , i is the cigarette pack number, μ i11 (x)μ i21 (x)μ i31 (x) represents multiple groups of first probabilities, μ i12 (x)μ i22 (x)μ i32 (x) represents multiple sets of second probabilities; The weights of multiple groups of first probabilities and multiple groups of second probabilities are recorded as A i ; Determine the first-level judgment vector B i =A i ×R i , the first-level judgment vector is used to characterize the smoke-interference state of each cigarette pack.

7. The method according to claim 6, characterized in that The step of determining the final smoke intermixing state according to the first-level judgment vector and the first-level weight matrix of the smoke intermixing state of each cigarette package includes: Determine the single factor evaluation matrix The first-level weight matrix of each cigarette pack's smoking status is recorded as A; Determine the secondary judgment vector B = A × R; According to the secondary judgment vector, the final smoke leakage state is determined.

8. A comprehensive evaluation device for smoke crosstalk, characterized in that: include: An acquisition unit, used to acquire the number of erroneous cigarette strips in each cigarette pack and the respective position information of the erroneous cigarette strips in each cigarette pack; A first determination unit is used to determine a plurality of groups of first probabilities and a plurality of groups of second probabilities according to the number of erroneous cigarettes in each cigarette pack and the respective position information of the erroneous cigarettes in each cigarette pack, wherein the plurality of groups of first probabilities are respective probabilities of a plurality of levels of cross-smoke occurrence corresponding to each cigarette pack determined according to the number of erroneous cigarettes in each cigarette pack, and the plurality of groups of second probabilities are respective probabilities of a plurality of levels of cross-smoke occurrence corresponding to each cigarette pack determined according to the respective position information of the erroneous cigarettes in each cigarette pack; The second determining unit is used to determine a final smoke intermixing state according to the multiple groups of first probabilities and the multiple groups of second probabilities.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the processor and the memory communicate with each other via a bus; The memory stores program instructions executable by the processor, and the processor can execute the method according to any one of claims 1 to 7 by calling the program instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images