CN112132495A - State machine quantization method, device, equipment and storage medium - Google Patents
State machine quantization method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112132495A CN112132495A CN201910553094.8A CN201910553094A CN112132495A CN 112132495 A CN112132495 A CN 112132495A CN 201910553094 A CN201910553094 A CN 201910553094A CN 112132495 A CN112132495 A CN 112132495A
- Authority
- CN
- China
- Prior art keywords
- event
- time
- point
- state
- quantization
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013139 quantization Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012790 confirmation Methods 0.000 claims description 4
- 238000004904 shortening Methods 0.000 abstract description 4
- 230000000875 corresponding effect Effects 0.000 description 86
- 238000010586 diagram Methods 0.000 description 13
- 238000001514 detection method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000035772 mutation Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000007704 transition Effects 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The method comprises the steps of grouping time state sequences on a first sliding window according to a first step length, determining point events corresponding to point event time in grouping, and shortening the length of a logistics event state sequence; and further, calculating a quantized value corresponding to the second step length on the second sliding window according to the quantized scalar value of the point event, and displaying the quantized value on the state machine. The state machine quantization method based on logistics event judgment provided by the embodiment of the application can solve the problems that a logistics event state sequence is long and event state misjudgment is easily caused, and can quantitatively display an original abstract logistics event state sequence to more intuitively represent a logistics event.
Description
Technical Field
The present invention relates generally to the field of logistics technology, and more particularly to a method, an apparatus, a device, and a storage medium for quantizing a state machine.
Background
With the progress and rapid development of society, people increasingly receive and send articles through logistics, which greatly facilitates the daily life of the masses.
When the incoming and outgoing items are transported at the transfer station, there are many situations in the logistics event, such as arrival, departure, and absence of vehicles, and work and rest of personnel. However, since the logistics event state sequence is long, the duration of a certain logistics event is uncertain, that is, the length of the state sequence is unknown, and misjudgment of the event state is easily caused.
However, an effective solution has not been proposed in the related art against the above-mentioned problems.
Disclosure of Invention
In view of the above-mentioned defects or shortcomings in the prior art, it is desirable to provide a state machine quantization method, device, apparatus and storage medium, which can not only solve the problems that the logistics event state sequence is long and the event state is easily misjudged, but also quantitatively display the original abstract logistics event state sequence, and more intuitively represent the logistics event.
In a first aspect, the present application provides a state machine quantization method based on logistic event determination, including:
grouping the time state sequences on a first sliding window according to a first step length, and determining point events corresponding to point event time in the grouping; wherein the point events are represented by quantized scalar values;
and calculating a quantized value corresponding to the second step length on a second sliding window according to the quantized scalar value of the point event, and displaying the quantized value on a state machine.
In a second aspect, the present application provides a state machine quantization apparatus based on logistics event determination, including:
the first sliding window assembly is used for grouping the time state sequences according to the first step length and determining point events corresponding to the point event time in the grouping; wherein the point events are represented by quantized scalar values;
and the second sliding window component is connected with the first sliding window component and used for calculating a quantized value corresponding to the second step length according to the quantized scalar value of the point event and displaying the quantized value on a state machine.
In a third aspect, the present application provides an apparatus comprising:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the state machine quantization method based on logistic event determination as described in the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program for implementing the state machine quantization method based on logistic event determination according to the first aspect.
In summary, the method, the apparatus, the device and the storage medium for quantifying a state machine based on logistics event determination provided by the embodiment of the present application are easy to cause misdetermination of an event state because the logistics event state sequence is long and the duration of a certain logistics event is uncertain, that is, the length of the state sequence is unknown; based on this, the embodiment of the application adopts a double-sliding-window structure, groups the time state sequences on the first sliding window according to the first step length, and determines the point event corresponding to the point event time in the group, thereby shortening the length of the logistics event state sequence; and then, on the second sliding window, according to the quantization scalar value of the point event, the quantization value corresponding to the second step length is calculated, and the quantization value is displayed on the state machine, so that the original abstract logistics event state sequence can be displayed in a quantization mode, and the logistics event can be represented more intuitively.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
fig. 1 is a schematic basic flowchart of a state machine quantization method based on logistics event determination according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a process for acquiring a time state sequence according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a state machine display provided by an embodiment of the present application;
fig. 4 is a schematic flowchart of another method for quantifying a state machine based on logistic event determination according to an embodiment of the present application;
fig. 5 is a state machine quantization apparatus based on logistic event determination according to an embodiment of the present application;
fig. 6 is a diagram of another state machine quantization apparatus based on logistic event determination according to an embodiment of the present application;
fig. 7 is a diagram of a state machine quantization apparatus based on logistic event determination according to an embodiment of the present application;
fig. 8 is a diagram of a state machine quantization apparatus based on logistic event determination according to an embodiment of the present application;
fig. 9 is a diagram illustrating a state machine quantization apparatus based on logistic event determination according to another embodiment of the present application;
fig. 10 is a computer system according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
The embodiment of the application provides a state machine quantization method based on logistics event judgment, and the method is applied to a state machine. For convenience of understanding and explanation, the method and the device for quantizing a state machine based on logistics event determination provided by the embodiment of the present application are described in detail below with reference to fig. 1 to 9.
Please refer to fig. 1, which is a schematic diagram illustrating a basic flow of a state machine quantization method based on logistic event determination according to an embodiment of the present application, the method includes the following steps:
s101, grouping the time state sequences on the first sliding window according to the first step length, and determining point events corresponding to the point event time in the grouping.
Wherein the point events are represented by quantized scalar values.
For example, the logistics event states are classified into 5 types, such as the first type is arrival, the second type is work, the third type is rest, the fourth type is departure, and the fifth type is no vehicle, and the quantitative scalar values corresponding to the 5 types of logistics event states are 4, 3, 2, 1, and 0, respectively. According to the rounding principle, when the equivalent scalar value is 3.5, the logistics event state is arrival; while the logistic event status is active when the normalized scalar value is 3.4. Of course, the quantization scalar value can be arbitrarily set according to actual needs, and this is not limited in this application embodiment.
Assuming that the first step length stride is 3, the time state sequence is grouped according to the first step length in the first sliding window, and then the grouping includes three continuous frame state sequence data, and the corresponding time is t, t +1, t + 2. In the embodiment of the present application, the time of the intermediate frame is selected as the point event time corresponding to the state sequence data of the three consecutive frames, that is, the point event time is t +1, and of course, any one time of the other two frames may be selected as the point event time. It should be noted that, in the embodiment of the present application, the value range of the first step is an odd number greater than or equal to 3.
For the determination of the point event, in the embodiment of the present application, a mode rule is firstly adopted, for example, when the continuous three-frame state sequence data is ABA, AAB, or BAA, since two or more states exist in the continuous three-frame state sequence data, that is, the number of times of occurrence of the state a is greater than that of occurrence of the state B, the point event is set as the point event corresponding to the state a.
Secondly, if the state sequence data of three continuous frames is ABC, that is, the occurrence frequency of each state is the same, for example, all states are 1, the priority rule is adopted for determining the time point event, the priority order is sorted according to the quantization scalar values of 5 types of logistics event states, and the larger the quantization scalar value is, the larger the priority is. For example, state a is working, and the corresponding quantization scalar value is 3; the state B is arrival, and the corresponding quantization scalar value is 4; state C is rest, and the corresponding quantization scalar value is 2; at this time, the priority order is state B, state a, and state C, and then the point event is set as the point event corresponding to state B. Because the interval time of the continuous three-frame state sequence data is short, the time of one frame can be selected as the point event time within the range of the allowed error; and the judgment of the logistics event is a long-term accumulation process, and the problem of detection mutation exists only according to the judgment of the single-frame image, so that the embodiment of the application selects the point event corresponding to the most possible state by comparing the state sequence data of three continuous frames, and reduces the influence caused by few single-frame detection mutation.
It should be noted that, as shown in fig. 2, the time state sequence in the embodiment of the present application is obtained through the following steps:
and S1011, acquiring single-frame images of the target vehicle at different moments, and associating the moments with the single-frame images.
For example, the camera captures a single frame image 1 of the target vehicle at time t, a single frame image 2 of the target vehicle at time t +1, and a single frame image 3 of the target vehicle at time t + 2.
S1012, based on the PeleNet classification network model, identifying the corresponding state of the single-frame image, and combining the time and the state into a time state sequence.
For example, a trained peloenet classification network model is used for detecting the tail of a target vehicle in a single-frame image and acquiring an envelope frame of the tail of the target vehicle; then, judging the lane to which the target vehicle belongs through the intersection point of the extension line of the track of the middle point of the bottom edge of the vehicle tail enveloping frame and the bottom edge of the single-frame image, and acquiring the area gradient of the target vehicle through the coordinates of the enveloping frames corresponding to the different time moments; further, the state of the target vehicle is determined based on a threshold value set for the area gradient of the target vehicle. The coordinates of the envelope frame are determined by the position of the camera and the position of the envelope frame in the single-frame image; each envelope frame of the target vehicle detected by the PeleNet classification network model is represented by four values, respectively, the smallest abscissa X in the horizontal direction of the envelope frame0The maximum horizontal axis X in the horizontal direction1Perpendicular toSmallest ordinate Y in direction0And the maximum ordinate Y in the vertical direction1. Because a plurality of lanes may appear in the image monitored by the camera in the moving process of the target vehicle, the lanes to which the target vehicle belongs are detected through the PeleNet classification network model, the running tracks of the non-target vehicle can be filtered, and the accuracy of measurement is improved.
It should be noted that the peloenet classification network model is a lightweight neural network, and can be applied to a mobile device. Due to the fact that the mobile device is convenient to use and carry, the state machine quantification method based on logistics event judgment in the embodiment of the application can be widely applied to different scenes.
And S102, calculating a quantized value corresponding to the second step length on the second sliding window according to the quantized scalar value of the point event, and displaying the quantized value on the state machine.
Wherein the second step is used to indicate the time between reporting of a logistic event in seconds, minutes, etc. For example, the second step size may be 7 seconds or 15 seconds, which is not limited in the embodiment of the present application.
For example, the initial time at which the point event starts on the second sliding window is t, and the quantization value sum of the time t is initial + rewarded alpha. Wherein initial is a quantized scalar value of a point event, and reward and alpha represent "reward and penalty" coefficients corresponding to a transition from one point event to the next. Specifically, k is set as a difference between a point event quantization scalar value at the time t +1 and a point event quantization scalar value at the time t, and the values of reward and alpha are shown in table 1.
TABLE 1 reward & penalty coefficient Table
| k | reward | alpha |
| 4 | 4/5 | 5/6 |
| 3 | 3/4 | 4/5 |
| 2 | 2/3 | 3/4 |
| 1 | 1/2 | 2/3 |
| 0 | 0 | 1 |
| -1 | -1/2 | 2/3 |
| -2 | -2/3 | 3/4 |
| -3 | -3/4 | 4/5 |
| -4 | -4/5 | 5/6 |
Assuming that the event at the time point t +1 is working, and the quantization scalar value corresponding to the working is 3, then initial is 3, and time point t +2 is rest, and the quantization scalar value corresponding to the rest is 2, then k is-1, and then the quantization value sum at the time point t +1 is 3+ (-1/2) (2/3) is 8/3; if the time t +3 is still at rest, the quantized value sum at the time t +2 is sum (last time) +0 × 1 is 8/3, and the quantized values sum corresponding to the respective times are added and averaged to obtain the final quantized value at the time t + 1. It should be noted that, since the events before and after the transition at different time points are correlated and not in a sudden change process, the initial value is added only at the beginning of the second step of the cycle, and the quantitative value at the subsequent time point is calculated based on the quantitative value at the previous time point, thereby ensuring the accuracy of the logistics event determination. Please refer to fig. 3, which is a schematic diagram of a state machine display according to an embodiment of the present disclosure. The abscissa represents time in seconds, and the ordinate represents a quantized value.
It should be noted that, in other embodiments of the present application, the quantized value may also be compared with a preset threshold interval, and a logistics event corresponding to the quantized value is determined; furthermore, the quantitative value and the logistics event are displayed on the state machine at the same time, so that the logistics event can be more intuitively represented. For example, when the quantization value is within a preset threshold interval (3.8, 4), the corresponding logistics event is arrival; when the quantized value is within a preset threshold interval (2.75, 3.25), the corresponding logistics event is working; when the quantized value is in a preset threshold interval (1.75, 2.25), the corresponding logistics event is rest; when the quantized value is within a preset threshold value interval (0.8, 1.2), the corresponding logistics event is departure; when the quantized value is within a preset threshold interval (0, 0.2), the corresponding logistics event is no vehicle. Compared with the current situation of judging the logistics event by manual participation, the embodiment of the application also improves the efficiency of judging the logistics event on the basis of ensuring the accuracy.
According to the state machine quantization method based on logistics event judgment, provided by the embodiment of the application, because the logistics event state sequence is long, the duration time of a certain logistics event is uncertain, namely the length of the state sequence is unknown, and misjudgment of the event state is easily caused; based on this, the embodiment of the application adopts a double-sliding-window structure, groups the time state sequences on the first sliding window according to the first step length, and determines the point event corresponding to the point event time in the group, thereby shortening the length of the logistics event state sequence; and then, on the second sliding window, according to the quantization scalar value of the point event, the quantization value corresponding to the second step length is calculated, and the quantization value is displayed on the state machine, so that the original abstract logistics event state sequence can be displayed in a quantization mode, and the logistics event can be represented more intuitively.
Based on the foregoing embodiment, a flow diagram of another state machine quantization method based on logistic event determination is provided in the embodiment of the present application, as shown in fig. 4, the method includes the following steps:
s401, dividing the time state sequence into at least one group according to a first step length, and selecting a first time in the group as a point event time.
For example, assuming that the first step length stride is 3, the time state sequence is grouped according to the first step length over the first sliding window, and then the grouping includes three consecutive frame state sequence data, and the corresponding times are t, t +1, and t +2, respectively. In the embodiment of the present application, the time of the intermediate frame is selected as the point event time corresponding to the state sequence data of the three consecutive frames, that is, the point event time is t +1, and of course, any one time of the other two frames may be selected as the point event time. It should be noted that, in the embodiment of the present application, the value range of the first step is an odd number greater than or equal to 3.
S402, determining a point event corresponding to the point event time based on a preset point event confirmation rule.
Specifically, in the embodiment of the present application, the number of times of each state in a packet is counted first, then the number of times is compared, and the state corresponding to the maximum number of times is used as a point event corresponding to a point event time, that is, a mode rule. For example, the consecutive three-frame status sequence data is ABA, AAB, or BAA, the number of times of occurrence of the status a in the consecutive three-frame status sequence data is two, and the number of times of occurrence of the status B is only one, and since the number of times of occurrence of the status a is greater than the number of times of occurrence of the status B, the point event is set as the point event corresponding to the status a.
In other embodiments of the present application, when the number of times is the same, a quantization scalar value corresponding to each state is obtained; and comparing the quantization scalar values, and taking the state corresponding to the maximum quantization scalar value as a point event corresponding to the point event time.
For example, if the state sequence data of three consecutive frames is ABC, that is, each state occurs the same number of times, for example, all states are 1, then the determination of the time point event adopts a priority rule, and the priority order is sorted according to the quantization scalar values of the 5 types of logistics event states, where the larger the quantization scalar value, the larger the priority. For example, state a is working, and the corresponding quantization scalar value is 3; the state B is arrival, and the corresponding quantization scalar value is 4; state C is rest, and the corresponding quantization scalar value is 2; at this time, the priority order is state B, state a, and state C, and then the point event is set as the point event corresponding to state B. Because the interval time of the continuous three-frame state sequence data is short, the time of one frame can be selected as the point event time within the range of the allowed error; and the judgment of the logistics event is a long-term accumulation process, and the problem of detection mutation exists only according to the judgment of the single-frame image, so that the embodiment of the application selects the point event corresponding to the most possible state by comparing the state sequence data of three continuous frames, and reduces the influence caused by few single-frame detection mutation.
And S403, calculating the difference value of the quantization scalar values of the adjacent point events, and acquiring the coefficient corresponding to the difference value from a preset table according to the difference value.
Specifically, k is set to be a difference value between a point event quantization scalar value at the time t +1 and a point event quantization scalar value at the time t, and the preset table is shown in table 1.
S404, based on the coefficient and the quantization scalar value at the initial time, a quantization value corresponding to the second step length is calculated.
Wherein the second step is used to indicate the time between reporting of a logistic event in seconds, minutes, etc. For example, the second step size may be 7 seconds or 15 seconds, which is not limited in the embodiment of the present application.
For example, assuming that the event at the time point t +1 is working, the quantization scalar value corresponding to the working is 3, then initial is 3, and time point t +2 is rest, and the quantization scalar value corresponding to the rest is 2, then k is-1, and then the quantization value sum at the time point t +1 is 3+ (-1/2) × (2/3) ═ 8/3; if the time t +3 is still at rest, the quantized value sum at the time t +2 is sum (last time) +0 × 1 is 8/3, and the quantized values sum corresponding to the respective times are added and averaged to obtain the final quantized value at the time t + 1. It should be noted that, since the events before and after the transition at different time points are correlated and not in a sudden change process, the initial value is added only at the beginning of the second step of the cycle, and the quantitative value at the subsequent time point is calculated based on the quantitative value at the previous time point, thereby ensuring the accuracy of the logistics event determination.
S405, comparing the quantized value with a preset threshold interval, and determining a logistics event corresponding to the quantized value.
For example, when the quantization value is within a preset threshold interval (3.8, 4), the corresponding logistics event is arrival; when the quantized value is within a preset threshold interval (2.75, 3.25), the corresponding logistics event is working; when the quantized value is in a preset threshold interval (1.75, 2.25), the corresponding logistics event is rest; when the quantized value is within a preset threshold value interval (0.8, 1.2), the corresponding logistics event is departure; when the quantized value is within a preset threshold interval (0, 0.2), the corresponding logistics event is no vehicle. Compared with the current situation of judging the logistics event by manual participation, the embodiment of the application also improves the efficiency of judging the logistics event on the basis of ensuring the accuracy.
And S406, simultaneously displaying the quantized value and the logistics event on the state machine.
It should be noted that, in other embodiments of the present application, a double check quantization mechanism may be further provided to prevent the influence of partial false detection and prevent the influence of a detection state mutation on the result of the state machine at a certain time. Namely, calculating the average value of the quantized values in the continuous time length, and determining the logistics event corresponding to the continuous time length based on the average value and a preset threshold interval. For example, when the quantization value of the continuous time length 7 is within a preset threshold interval (3.8, 4), the corresponding logistics event is arrival; when the quantitative value with the continuous time length of 11 is in a preset threshold interval (2.75, 3.25), the corresponding logistics event is working; when the quantitative value with the continuous time length of 11 is in a preset threshold interval (1.75, 2.25), the corresponding logistics event is rest; when the quantitative value with the continuous time length of 5 is in a preset threshold interval (0.8, 1.2), the corresponding logistics event is departure; when the quantitative value of the continuous time length 7 is in a preset threshold interval (0, 0.2), the corresponding logistics event is no vehicle. For the judgment of the loading and unloading event, the corresponding loading rate change is determined in the working interval, namely if the loading rate does not change in the selected time period T, the corresponding logistics event is working; when the loading rate is increased, the corresponding logistics event is loading; the loading rate becomes smaller and the corresponding logistic event is unloading.
The state machine quantization method based on logistics event judgment provided by the embodiment of the application can solve the problems that a logistics event state sequence is long and misjudgment of an event state is easily caused, and can quantitatively display an original abstract logistics event state sequence to more intuitively represent a logistics event.
Based on the foregoing embodiments, the present application provides a state machine quantization apparatus based on logistics event determination, and the apparatus may be applied to the state machine quantization method based on logistics event determination provided in the embodiments corresponding to fig. 1 to 4. Referring to fig. 5, the state machine quantization apparatus 5 based on logistic event determination includes:
and the first sliding window component 51 is used for grouping the time state sequences according to the first step length and determining the point event corresponding to the point event time in the grouping.
Wherein the point events are represented by quantized scalar values.
It should be noted that in the embodiment of the present application, single-frame images of a target vehicle are acquired at different times, and the times are associated with the single-frame images; further, based on the PeleNet classification network model, states corresponding to the single-frame images are identified, and the time and the states are combined into a time state sequence.
And the second sliding window component 52 is connected with the first sliding window component and is used for calculating a quantized value corresponding to the second step length according to the quantized scalar value of the point event and displaying the quantized value on the state machine.
In other embodiments of the present application, as shown in fig. 6, the first sliding window assembly 51 includes:
the grouping unit 511 is configured to divide the time state sequence into at least one group according to a first step, and select a first time in the group as a point event time;
the determining unit 512 is configured to determine a point event corresponding to the point event time based on a preset point event confirmation rule.
In other embodiments of the present application, the determining unit 512 is specifically configured to count the number of times of each state in the packet; further, the magnitude of the count is compared, and the state corresponding to the maximum count is taken as the point event corresponding to the point event time.
In other embodiments of the present application, the determining unit 512 is further configured to obtain a quantization scalar value corresponding to each state when the number of times is the same; and comparing the quantization scalar values, and taking the state corresponding to the maximum quantization scalar value as a point event corresponding to the point event time.
In other embodiments of the present application, as shown in FIG. 7, the second sliding window assembly 52 comprises:
the first calculating unit 521 is configured to calculate a difference between quantized scalar values of adjacent point events, and obtain a coefficient corresponding to the difference from a preset table according to the difference;
the second calculating unit 522 is configured to calculate a quantized value corresponding to the second step size based on the coefficient and the quantized scalar value at the initial time.
In other embodiments of the present application, as shown in fig. 8, the state machine quantization apparatus 5 based on logistic event determination further includes:
the first determining module 53 is configured to compare the quantized value with a preset threshold interval, and determine a logistics event corresponding to the quantized value;
and a display module 54 for displaying the quantified value and the logistics event on the state machine at the same time.
In other embodiments of the present application, as shown in fig. 9, the state machine quantization apparatus 5 based on logistic event determination further includes:
a calculation module 55 for calculating an average of the quantized values over successive time periods;
and a second determining module 56, configured to determine, based on the average value and a preset threshold interval, a logistics event corresponding to the continuous time length.
According to the state machine quantification device based on logistics event judgment, due to the fact that the logistics event state sequence is long, the duration time of a certain logistics event is not determined, namely the length of the state sequence is unknown, and misjudgment of an event state is easily caused; based on this, the embodiment of the application adopts a double-sliding-window structure, and the first sliding window component is used for grouping the time state sequences according to the first step length, determining the point event corresponding to the point event time in the grouping, and shortening the length of the logistics event state sequences; furthermore, the second sliding window component is used for calculating a quantized value corresponding to the second step length according to the quantized scalar value of the point event, displaying the quantized value on the state machine, and displaying the original abstract logistics event state sequence in a quantized mode, so that the logistics event can be represented more intuitively.
Based on the foregoing embodiments, the present application provides an apparatus, which includes one or more processors; a memory for storing one or more programs.
The one or more programs, when executed by the one or more processors, cause the one or more processors to perform the above-described state machine quantization method based on logistic event determinations.
Based on the foregoing embodiments, the present application provides a computer system. Referring to fig. 10, the computer system 1000 includes a Central Processing Unit (CPU)1001 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)1002 or a program loaded from a storage section into a Random Access Memory (RAM) 1003. In the RAM1003, various programs and data necessary for system operation are also stored. The CPU1001, ROM1002, and RAM1003 are connected to each other via a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.
The following components are connected to the I/O interface 1005: an input section 1006 including a keyboard, a mouse, and the like; an output section 1007 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 1008 including a hard disk and the like; and a communication section 1009 including a network interface card such as a LAN card, a modem, or the like. The communication section 1009 performs communication processing via a network such as the internet. The driver 1010 is also connected to the I/O interface 1005 as necessary. A removable medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1010 as necessary, so that a computer program read out therefrom is mounted into the storage section 1008 as necessary.
In particular, according to embodiments of the present application, the processes described above with reference to flow diagrams 1, 2 and 4 may be implemented as computer software programs. For example, embodiment 1 of the present application includes a computer program product including a computer program carried on a computer-readable medium, the computer program being executed by the CPU1001 to implement the steps of:
grouping the time state sequences on a first sliding window according to the first step length, and determining point events corresponding to the point event time in the grouping; wherein, the point event is represented by a quantized scalar value;
and calculating a quantized value corresponding to the second step length on the second sliding window according to the quantized scalar value of the point event, and displaying the quantized value on the state machine.
In such an embodiment, the computer program may be downloaded and installed from a network through the communication part 1009 and/or installed from the removable medium 1011.
It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of state machine quantization systems, methods and computer program products based on logistic event determination according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves. The described units or modules may also be provided in a processor, and may be described as: a processor includes a first sliding window assembly and a second sliding window assembly. Wherein the designation of a unit or module does not in some way constitute a limitation of the unit or module itself.
As another aspect, the present application also provides a computer-readable medium, which may be contained in the terminal described in the above embodiments; or may exist separately and not be assembled into the terminal. The computer readable medium carries one or more programs which, when executed by the terminal, cause the terminal to implement the state machine quantization method based on logistics event determination as in the above embodiments.
For example, the terminal may implement the following as shown in fig. 1: s101, grouping the time state sequences on a first sliding window according to a first step length, and determining point events corresponding to point event time in the grouping; wherein, the point event is represented by a quantized scalar value; and S102, calculating a quantized value corresponding to the second step length on the second sliding window according to the quantized scalar value of the point event, and displaying the quantized value on the state machine. As another example, the terminal may implement the steps shown in fig. 2 and fig. 4.
It should be noted that although in the above detailed description several modules or units of the terminal for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
Moreover, although the steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that the steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by a person skilled in the art that the scope of the invention as referred to in the present application is not limited to the embodiments with a specific combination of the above-mentioned features, but also covers other embodiments with any combination of the above-mentioned features or their equivalents without departing from the inventive concept. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (10)
1. A state machine quantization method based on logistic event determination, the method comprising:
grouping the time state sequences on a first sliding window according to a first step length, and determining point events corresponding to point event time in the grouping; wherein the point events are represented by quantized scalar values;
and calculating a quantized value corresponding to the second step length on a second sliding window according to the quantized scalar value of the point event, and displaying the quantized value on a state machine.
2. The state machine quantization method based on logistics event determination of claim 1, characterized in that the time state sequence is obtained by the following steps:
acquiring single-frame images of a target vehicle at different moments, and associating the moments with the single-frame images;
and identifying the corresponding state of the single-frame image based on a PeleNet classification network model, and combining the time and the state into the time state sequence.
3. The method for quantizing a state machine based on logistics event judgment according to claim 1, wherein the grouping time state sequences according to a first step length on a first sliding window and determining the point event corresponding to the point event time in the grouping comprises:
dividing the time state sequence into at least one group according to the first step length, and selecting first time in the group as the point event time;
and determining the point event corresponding to the point event time based on a preset point event confirmation rule.
4. The method for quantizing a state machine based on logistic event determination according to claim 3, wherein the determining the point event corresponding to the point event time based on a preset point event confirmation rule includes:
counting the number of times of each state in the packet;
and comparing the times, and taking the state corresponding to the maximum times as the point event corresponding to the point event time.
5. The method of state machine quantization based on logistic event decision as defined in claim 4, further comprising:
when the times are the same, acquiring the quantization scalar value corresponding to each state;
and comparing the magnitude of the quantization scalar value, and taking the state corresponding to the maximum quantization scalar value as the point event corresponding to the point event time.
6. The method of claim 1, wherein calculating a quantization value corresponding to a second step size according to the quantization scalar value of the point event over the second sliding window comprises:
calculating a difference value of quantization scalar values of adjacent point events, and acquiring a coefficient corresponding to the difference value from a preset table according to the difference value;
and calculating a quantization value corresponding to the second step length based on the coefficient and the quantization scalar value at the initial moment.
7. The method of state machine quantization based on logistic event decision according to any one of claims 1 to 6, characterized in that the method further comprises:
comparing the quantized value with a preset threshold interval, and determining a logistics event corresponding to the quantized value;
displaying the quantified value and the logistics event on the state machine simultaneously.
8. A state machine quantization apparatus based on logistic event decision, the apparatus comprising:
the first sliding window assembly is used for grouping the time state sequences according to the first step length and determining point events corresponding to the point event time in the grouping; wherein the point events are represented by quantized scalar values;
and the second sliding window component is connected with the first sliding window component and used for calculating a quantized value corresponding to the second step length according to the quantized scalar value of the point event and displaying the quantized value on a state machine.
9. An apparatus, characterized in that the apparatus comprises:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the state machine quantization method based on logistic event determination of any of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon for implementing the state machine quantization method based on logistic event decision according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910553094.8A CN112132495B (en) | 2019-06-25 | 2019-06-25 | State machine quantization method, device, equipment and medium based on logistics event judgment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910553094.8A CN112132495B (en) | 2019-06-25 | 2019-06-25 | State machine quantization method, device, equipment and medium based on logistics event judgment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112132495A true CN112132495A (en) | 2020-12-25 |
| CN112132495B CN112132495B (en) | 2024-06-07 |
Family
ID=73849250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910553094.8A Active CN112132495B (en) | 2019-06-25 | 2019-06-25 | State machine quantization method, device, equipment and medium based on logistics event judgment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112132495B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005026978A2 (en) * | 2003-09-11 | 2005-03-24 | Siemens Aktiengesellschaft | Method for determining a rate with the aid of a time weighted moving average |
| CN101483547A (en) * | 2009-02-12 | 2009-07-15 | 中国人民解放军信息工程大学 | Evaluation method and system for network burst affair |
| CN104459797A (en) * | 2013-09-22 | 2015-03-25 | 中国石油化工股份有限公司 | Method for recognizing and collecting microseism events in well |
| US20180307544A1 (en) * | 2017-04-21 | 2018-10-25 | International Business Machines Corporation | Event sequence management |
| CN109033964A (en) * | 2018-06-22 | 2018-12-18 | 顺丰科技有限公司 | It is a kind of judgement vehicle to departure from port event method, system and equipment |
| CN109387712A (en) * | 2018-10-09 | 2019-02-26 | 厦门理工学院 | Non-intrusion type cutting load testing and decomposition method based on state matrix decision tree |
| CN109493573A (en) * | 2018-11-21 | 2019-03-19 | 杭州安恒信息技术股份有限公司 | User's customized event alarm method and system based on time slide window |
-
2019
- 2019-06-25 CN CN201910553094.8A patent/CN112132495B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005026978A2 (en) * | 2003-09-11 | 2005-03-24 | Siemens Aktiengesellschaft | Method for determining a rate with the aid of a time weighted moving average |
| CN101483547A (en) * | 2009-02-12 | 2009-07-15 | 中国人民解放军信息工程大学 | Evaluation method and system for network burst affair |
| CN104459797A (en) * | 2013-09-22 | 2015-03-25 | 中国石油化工股份有限公司 | Method for recognizing and collecting microseism events in well |
| US20180307544A1 (en) * | 2017-04-21 | 2018-10-25 | International Business Machines Corporation | Event sequence management |
| CN109033964A (en) * | 2018-06-22 | 2018-12-18 | 顺丰科技有限公司 | It is a kind of judgement vehicle to departure from port event method, system and equipment |
| CN109387712A (en) * | 2018-10-09 | 2019-02-26 | 厦门理工学院 | Non-intrusion type cutting load testing and decomposition method based on state matrix decision tree |
| CN109493573A (en) * | 2018-11-21 | 2019-03-19 | 杭州安恒信息技术股份有限公司 | User's customized event alarm method and system based on time slide window |
Non-Patent Citations (2)
| Title |
|---|
| 丁世敬 等: "基于事件检测的非侵入式负荷识别方法研究", 建筑电气, no. 07 * |
| 刘海龙 等: "乱序RFID数据流上的复杂事件检测方法", 西北工业大学学报, no. 04 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112132495B (en) | 2024-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108256506B (en) | Method and device for detecting object in video and computer storage medium | |
| JP7436670B2 (en) | Target detection method, device, and roadside equipment in road-vehicle coordination | |
| CN109214253B (en) | Video frame detection method and device | |
| CN109508621B (en) | Method, device and equipment for monitoring state of loading and unloading port and storage medium thereof | |
| CN113554008A (en) | Method and device for detecting static object in area, electronic equipment and storage medium | |
| CN113822110B (en) | Target detection method and device | |
| CN112132495B (en) | State machine quantization method, device, equipment and medium based on logistics event judgment | |
| CN115830012B (en) | Method for detecting and analyzing clue damage data of overhead contact system | |
| CN112749647A (en) | Intelligent cash-receiving inspection method and system based on monitoring video | |
| CN116304910A (en) | Anomaly detection method, device, equipment and storage medium for operation and maintenance data | |
| CN114676168A (en) | Data tracking method and device, electronic equipment and storage medium | |
| CN114137635A (en) | Method, device and equipment for testing detection efficiency of security check machine and storage medium | |
| CN113963310A (en) | People flow detection method and device for bus station and electronic equipment | |
| CN112990645A (en) | Non-limiting passenger flow demand determination method and related equipment | |
| CN109903281B (en) | Multi-scale-based target detection method and device | |
| CN114637868B (en) | Product data processing method and system applied to fast-moving industry | |
| CN115985103A (en) | Method and system for predicting duration of traffic incident | |
| CN113704643B (en) | Method and device for determining state of target object, electronic equipment and storage medium | |
| EP3886020A1 (en) | System and method for geofence based cycle time determination | |
| CN113780966B (en) | Method and device for generating loading and unloading operation residual time information | |
| CN114056389B (en) | Train warehouse-in and warehouse-out monitoring method and device and electronic equipment | |
| CN118262507A (en) | Traffic jam detection method, system, computer equipment and storage medium | |
| CN111401104B (en) | Classification model training method, classification method, device, equipment and storage medium | |
| CN114445323A (en) | Damaged package detection method and device, computer equipment and storage medium | |
| CN116152597A (en) | Training method and device for target detection model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |