Automatic piece counting method and system for sewing apparatus

Abstract

The sewing equipment automatic piece counting method and system of the present application automatically analyzes and processes the collected sewing data by using an automatic piece counting analysis method related to the complexity of the process of the collected sewing data to obtain the process piece number corresponding to the sewing data. The present application can select the corresponding automatic piece counting analysis method according to the complexity of the process of the sewing equipment to realize accurate piece counting for sewing data with different process complexities.

Description

TECHNICAL FIELD

[0001] The present application relates to the sewing technical field, in particular to a sewing equipment automatic piece counting method and system. BACKGROUND

[0002] At present, the sewing equipment cannot realize the automatic piece counting function, and the piece counting of the sewing equipment operated by the workers is mostly recorded by hand, which is tedious and prone to errors. With the development of the Internet of Things technology of the sewing equipment, the sewing data generated in the operation process of the Internet of Things sewing equipment can be collected and recorded, and then analyzed and processed by artificial intelligence related technology methods, so as to realize the automatic piece counting function of the sewing equipment. However, the existing automatic piece counting method generally adopts a simple sewing process piece counting mode for piece counting, and the piece counting result obtained for a complex process is not accurate, and accurate automatic piece counting cannot be performed on processes with different complexity. SUMMARY

[0003] In view of the above-mentioned shortcomings of the prior art, the purpose of the present application is to provide a sewing equipment automatic piece counting method and system, which can solve the problem that the prior art cannot accurately and automatically count pieces for processes with different complexity.

[0004] To achieve the above-mentioned purpose and other related purposes, the present application provides a sewing equipment automatic piece counting method, which comprises: acquiring sewing data collected by a sewing equipment; wherein the sewing data comprises: a time stamp, a needle number and a sewing state; and performing automatic piece counting analysis and processing on the sewing data by using an automatic piece counting analysis mode related to the complexity of the process of the sewing data, to obtain the process piece number corresponding to the sewing data; wherein the type of the automatic piece counting analysis mode comprises: a simple sewing process piece counting mode and a complex sewing process piece counting mode.

[0005] In an embodiment of the present application, the automatic piece counting analysis mode comprises: performing simple sewing process piece counting analysis and processing on the sewing data based on a simple sewing process piece counting model, to obtain the process piece number corresponding to the sewing data.

[0006] In an embodiment of the present application, the way of performing simple sewing process piece counting analysis and processing on the sewing data to obtain the process piece number corresponding to the sewing data comprises: judging the process piece number corresponding to the sewing data based on similar needle number values identified according to the sewing data and the frequency of occurrence of each time interval.

[0007] In an embodiment of the present application, the method for determining the number of pieces of the sewing process based on the similarity of the needle values and the frequency of the time intervals includes: grouping the sewing data to obtain one or more data groups; obtaining the time intervals between adjacent data groups and the accumulated needle values of each group, and counting the similarity of the needle values and the frequency of the time intervals to obtain the convergence time interval and the convergence needle value; and determining the number of pieces of the sewing process based on the convergence time interval and the convergence needle value.

[0008] In an embodiment of the present application, the method for determining the number of pieces of the complex sewing process includes: performing complex sewing process piece counting analysis on the sewing data based on a complex sewing process piece counting model to obtain the number of pieces of the sewing process.

[0009] In an embodiment of the present application, the method for determining the number of pieces of the complex sewing process includes: performing complex sewing process piece counting analysis on the sewing data based on a complex sewing process piece counting model to obtain the number of pieces of the sewing process.

[0010] In an embodiment of the present application, the method for determining the number of pieces of the complex sewing process based on the standard flow feature data includes: determining the sewing data of one or more standard pieces of work in the sewing data to obtain the standard flow feature data corresponding to one piece of work; string encoding the sewing data in units of sewing edges according to the standard needle values of the sewing edges; dividing the sewing data into one or more standard data windows and one or more detection data windows based on the standard flow feature data; each standard data window corresponds to a standard string encoding segment; each detection data window corresponds to a detection string encoding segment; and performing encoding conversion distance calculation on the detection string encoding segment corresponding to each detection data window and the standard string encoding segment based on a similarity algorithm, and taking the number of detection data windows with a conversion distance less than a threshold as the number of pieces of the sewing data.

[0011] In an embodiment of the present application, the similarity algorithm uses the Levenshtein similarity algorithm.

[0012] In an embodiment of the present application, the sewing state includes one or more of the motor start / stop state, the thread cutting state, and the presser foot lifting state.

[0013] To achieve the above object and other related objects, the present application provides a sewing equipment automatic piece counting system, which comprises: a sewing data acquisition module, configured to acquire sewing data collected by a sewing equipment; wherein the sewing data comprises: a time stamp, a needle number and a sewing state; and an automatic piece counting module, connected to the sewing data acquisition module, configured to perform automatic piece counting analysis on the sewing data by using an automatic piece counting analysis mode related to the complexity of a procedure of the sewing data, to obtain a procedure piece number corresponding to the sewing data; wherein the type of the automatic piece counting analysis mode comprises: a simple sewing procedure piece counting mode and a complex sewing procedure piece counting mode.

[0014] As described above, the sewing equipment automatic piece counting method and system of the present application have the following beneficial effects: the present application performs automatic piece counting analysis on collected sewing data by using an automatic piece counting analysis mode related to the complexity of a procedure of the sewing data, to obtain a procedure piece number corresponding to the sewing data. The present application can select a corresponding automatic piece counting analysis mode according to the complexity of a procedure of a sewing equipment, to realize accurate piece counting for sewing data of different procedure complexities. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 A flowchart of a sewing equipment automatic piece counting method in an embodiment of the present application is shown.

[0016] Figure 2 A schematic diagram of sewing data in an embodiment of the present application is shown.

[0017] Figure 3 A schematic diagram of a pocket procedure in an embodiment of the present application is shown.

[0018] Figure 4 A schematic diagram of a pocket procedure in an embodiment of the present application is shown.

[0019] Figure 5 A schematic diagram of sewing data acquisition in an embodiment of the present application is shown.

[0020] Figure 6 A flowchart of piece counting using a self-learning model in an embodiment of the present application is shown.

[0021] Figure 7 A structural schematic diagram of a sewing equipment automatic piece counting system in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] The advantages and features of the present application will become apparent from the following description of embodiments of the present application, which is given for the sake of a better understanding of the application, and no limitation of the present application is intended to be implied by the description of a certain embodiment or by the use of a certain terminology. It is also to be understood that other embodiments can be used and that structural, electrical, as well as other changes can be made without departing from the spirit or the scope of the present application. It is intended to include all such changes and alternatives within the scope of the present application. It should be noted that, in the following description of embodiments of the present application, the same elements have the same last two digits of the reference numbers.

[0023] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting, unless otherwise specified. Spatially relative terms, such as "upper," "lower," "left," "right," "below," "below," "bottom," "top," and the like, can be used herein for ease of description to describe one element or feature's relationship to another element(s) or feature(s) as illustrated in the figures. It will be further understood that the spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientations depicted in the figures. For example, if a device described is turned over in use, a relative prefi x or suffix used with a

[0024] Throughout this specification, when it is said that a certain part is "connected" to another part, it includes not only the case of "direct connection" but also the case of "indirect connection" in which other elements are interposed therebetween. In addition, when it is said that a certain part "includes" a certain component, other components are not excluded unless it is specifically stated to the contrary, and it means that other components can be further included.

[0025] The terms first, second, third, etc. that are used herein are used only for explanation of various parts, components, regions, layers and / or sections, and are not limited thereto. These terms are used only to distinguish a certain part, component, region, layer or section from another part, component, region, layer or section. Therefore, the first part, component, region, layer or section described below can be referred to as the second part, component, region, layer or section within the scope of the present application.

[0026] Furthermore, as used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context indicates otherwise. It should be further understood that the terms “comprising,” “including,” indicate the presence of the stated feature, operation, element, component, item, kind, and / or group, but do not preclude the presence, occurrence, or addition of one or more other features, operations, elements, components, items, kinds, and / or groups. The terms “or” and “and / or” as used herein are interpreted as inclusive, or mean any one or any combination thereof. Thus, “A, B, or C” or “A, B, and / or C” means “any one of: A; B; C; A and B; A and C; B and C; A, B, and C.” Exceptions to this definition arise only when combinations of elements, functions, or operations are inherently mutually exclusive in some manner.

[0027] This invention provides an automatic piece counting method for sewing equipment. By employing an automatic piece counting analysis method related to the complexity of the sewing process, the collected sewing data is automatically analyzed to obtain the number of pieces corresponding to the sewing data. This invention can select the appropriate automatic piece counting analysis method based on the complexity of the sewing equipment's processes, thereby achieving accurate piece counting for sewing data with varying levels of process complexity.

[0028] The present invention will now be described in detail with reference to the accompanying drawings, so that those skilled in the art can readily implement it. The present invention can be embodied in many different forms and is not limited to the embodiments described herein.

[0029] like Figure 1 The diagram shown illustrates a flowchart of the automatic piece counting method for sewing equipment according to an embodiment of the present invention.

[0030] The method includes:

[0031] Step S11: Obtain sewing data collected by the sewing equipment.

[0032] In detail, the sewing data includes: timestamps, stitch counts, and sewing status; specifically, it includes the sewing status and stitch count corresponding to each timestamp.

[0033] Optionally, the sewing state includes one or more of the following: motor start / stop state, thread cutting state, and presser foot lifting state.

[0034] Optional, such as Figure 2 As shown, the timeline in the acquired sewing data records time nodes (time stamps) below and sewing status (including but not limited to motor start / stop, thread cutting, presser foot lifting, etc.) above. For example, each time the sewing equipment starts or stops, it assigns a current timestamp and also records the number of stitches produced during each start / stop period.

[0035] Step S12: automatically analyzing the sewing data by using an automatic piece analysis mode related to the complexity of the sewing data, to obtain the piece number corresponding to the sewing data.

[0036] In detail, the type of the automatic piece analysis mode includes a simple sewing process piece analysis mode and a complex sewing process piece analysis mode. That is, when the complexity of the sewing data is simple, the simple sewing process piece analysis mode is used to automatically analyze the sewing data; when the complexity of the sewing data is complex, the complex sewing process piece analysis mode is used to automatically analyze the sewing data.

[0037] To further illustrate the simple sewing process piece analysis mode, the following embodiment is provided.

[0038] Optionally, the automatic piece analysis mode includes: performing simple sewing process piece analysis on the sewing data based on a simple sewing process piece analysis model, to obtain the piece number corresponding to the sewing data.

[0039] The simple sewing process piece analysis model is trained by a simple piece analysis sample set, wherein the simple piece analysis sample set includes a plurality of sewing data samples corresponding to simple sewing processes and corresponding piece numbers.

[0040] Optionally, the way of performing simple sewing process piece analysis on the sewing data to obtain the piece number corresponding to the sewing data includes: judging the piece number corresponding to the sewing data based on the similar needle number value identified from the sewing data and the frequency of occurrence of each time interval.

[0041] Optionally, the way of judging the piece number corresponding to the sewing data based on the similar needle number value identified from the sewing data and the frequency of occurrence of each time interval includes:

[0042] grouping the sewing data into similar data groups to obtain one or more data groups;

[0043] The time interval between each adjacent data group and the needle count value accumulated by each group are obtained, and similar needle count values and the frequency of each time interval are counted to obtain a convergence time interval and a convergence needle count value; when the sewing operator is normally operating, the time interval between the groups of sewing data should be a certain value close to the convergence value, and the frequency of the value should be the highest, so the convergence time interval converging to the value can be used as one of the judgment criteria. When the sewing operator appears to rework or take materials, the time interval between the groups will deviate far from the convergence value, at which time the needle count value of the group is used for secondary judgment. Because the needle count of a completed process by the sewing operator will converge to a certain range value, i.e., the convergence needle count value, the group in which the needle count value range appears should be the most, so the convergence needle count value converging to the value can be used as another judgment criterion.

[0044] Based on the convergence time interval and the convergence needle count value, the number of process pieces corresponding to the sewing data is determined according to the sewing data. That is, the number of process pieces corresponding to the sewing data is determined by using the two judgment criteria of the convergence time interval and the convergence needle count value.

[0045] Optionally, the meanshift algorithm is used to group the similar data of the sewing data.

[0046] In order to further illustrate the complex sewing process piece counting method, the following embodiments are provided.

[0047] Optionally, the complex sewing process piece counting method comprises: based on a complex sewing process piece counting model, the sewing data is subjected to complex sewing process piece counting analysis and processing to obtain the number of process pieces corresponding to the sewing data.

[0048] The complex sewing process piece counting model is trained by a complex piece counting sample set, wherein the complex piece counting sample set comprises a plurality of sewing data samples corresponding to complex sewing processes and corresponding process piece numbers.

[0049] Optionally, the way of subjecting the sewing data to complex sewing process piece counting analysis and processing to obtain the number of process pieces corresponding to the sewing data comprises:

[0050] Based on the standard flow feature data of the corresponding standard process piece marked in the sewing data, the number of process pieces corresponding to the sewing data is determined; wherein the standard flow data comprises a standard needle count value, a standard time stamp and a standard sewing state of each sewing edge. That is, the sewing edge situation is determined by using the standard flow feature data of the corresponding standard process piece marked in the sewing data, and then the sewing edge similarity situation in the sewing data is solved based on the sewing edge situation to determine the number of process pieces.

[0051] Optionally, the way of judging the number of process pieces corresponding to the sewing data based on the standard process feature data calibrated in the sewing data comprises:

[0052] Firstly, the process content of completing a number of process pieces needs to be set, which can be a single process or a combination of multiple processes. Then, the standard operation process corresponding to completing a number of process pieces is determined. The so-called standard operation process refers to the sewing process that has a fixed sewing order and is executed by the sewing operator to complete a number of process pieces. Through the standard operation process, each sewing edge can be split according to the fixed sewing order, so as to mark the number of stitches of each sewing edge. The edges with similar number of stitches are defined as similar edges, and then completing a number of process pieces can be converted into sewing all edges.

[0053] Therefore, it is necessary to first determine the sewing data of one or more standard process pieces in the sewing data to obtain the standard process feature data corresponding to one process piece; for example, the sewing data of one or three standard process pieces (the first three pieces) is determined in the sewing data; the standard process feature data corresponding to one process piece is determined in combination with the sewing data of the three standard process pieces; this way can also play a new process starting prompt role when a new process piece is sewn.

[0054] The sewing data is string encoded in units of sewing edges according to the standard number of stitches of each sewing edge; for example, as shown in Figure 3 Each sewing edge is letter encoded and stitch number recorded, and then the sewing equipment operator is instructed to start sewing edge a and sequentially sew edges a-j, which are completed as a number of process pieces, i.e. a set of standard operation process. The sewing equipment will record and transmit the generated sewing data (stitch number, thread cutting, presser foot lifting, etc.) in real time during the process of sewing edges a-j. As shown in Figure 4 The similar edges with similar number of stitches are replaced by the same code, and then the edge number code of sewing a pocket is converted to A-E, and the standard code of completing the pocket process is ABBACDEEDC.

[0055] Based on the standard process feature data, the sewing data is divided into one or more standard data windows and one or more detection data windows similar to the standard data windows; wherein each standard data window corresponds to a standard string encoding segment; each detection data window corresponds to a detection string encoding segment; and the standard data window corresponds to the standard process feature data. It should be noted that the number of standard data windows is determined according to the number of sewing data of the determined standard process pieces.

[0056] The detection string coding segment corresponding to each detection data window is compared with the standard string coding segment, and the detection data window meeting the comparison condition is counted as a piece of process piece, and finally the number of process pieces is obtained.

[0057] Optionally, the actual operator does not completely follow the standard operation process for sewing, and there are also repeated sewing and abnormal sewing phenomena. Therefore, the comparison of the detection string coding segment corresponding to each detection data window with the standard string coding segment includes:

[0058] Based on the similarity algorithm, the detection string coding segment corresponding to each detection data window is respectively compared with the standard string coding segment for coding conversion distance calculation, and the number of detection data windows less than the conversion distance threshold is taken as the process piece number corresponding to the sewing data. For example, the standard string coding segment for completing the pocket process is ABBACDEEDC. The actual sewing operator does not completely follow the standard operation process for sewing, and different coding conditions such as BBACDEEDCA and BACDEEDCAB are generated. That is, based on the similarity algorithm, the detection string coding segment corresponding to each detection data window is respectively compared with the standard string coding segment for coding conversion distance calculation, that is, the minimum conversion distance of ABBACDEEDC and BBACDEEDCA is 2. When the minimum conversion distance is less than a certain set value, for example, 3 (the selection of the set value can be obtained by fitting the sewing data), it is considered that one process sewing is completed.

[0059] Preferably, the similarity algorithm uses the Levenshtein similarity algorithm. For example, using the Levenshtein similarity algorithm to calculate the minimum conversion distance of two codes kitten and sitting is 3, the first step kitten becomes sitten, the second step sitten becomes sittin, and the third step sittin becomes sitting.

[0060] Optionally, the simple sewing process piece counting model and the complex sewing process piece counting model can be set in a local device or a cloud platform.

[0061] In order to better describe the automatic piece counting method of the sewing equipment, the following specific embodiments are provided for illustration;

[0062] Embodiment 1: Internet of Things sewing equipment piece counting method based on artificial intelligence.

[0063] The method comprises:

[0064] Step 1: Obtain the sewing data collected by the sewing equipment; such as Figure 5The acquisition process of sewing data is shown. The sewing data generated by the Internet of Things sewing equipment 1 during the operation process can be transmitted or stored through the communication device 2. The communication device 2 can upload the received or stored sewing data to the cloud platform 3. The collected sewing data records the time node below the time axis and records the sewing equipment state information (including but not limited to motor start-stop, thread trimming, foot lifting, etc.) above the time axis. The Internet of Things sewing equipment is assigned with the current time point each time it starts or stops, and the number of stitches generated during each start-stop is also recorded. Then each time point and the number of stitches are uploaded as real-time sewing data.

[0065] Step 2: For simple repetitive sewing processes, a self-learning model can be applied to automatically analyze and process the sewing data of the Internet of Things sewing equipment. The number of process pieces is determined by the time difference and the number of stitches obtained by grouping similar data. For example, Figure 6 The self-learning model example is shown. The sewing data can be directly processed to analyze the number of process pieces completed. First, the sewing data of the Internet of Things sewing equipment is grouped by the Mainshift meanshift algorithm, that is, similar data images are grouped, and then the time difference between adjacent groups and the cumulative stitch value of each group can be obtained. Finally, the interval time difference between groups and the stitch value of the group are used to determine the number of process pieces.

[0066] Step 3: For more complex sewing processes, a supervised model can be applied to calibrate the sewing edge situation, and then the similarity of the sewing data is solved to determine the number of process pieces. That is, the sewing data of the standard operation process (including time nodes, stitch numbers, thread trimming, motor start-stop, etc.) is sampled, and the characteristic information of the sample data is recorded. Then the sewing data (including sample data) of the Internet of Things sewing equipment is string encoded, and then the data window similar to the sample data on the time axis of the sewing data is intercepted. Then the Levenshtein similarity algorithm is applied to obtain the distance value that can be converted between the two. Therefore, when the distance value is within a certain range, it is determined that the intercepted sewing data and the sample data complete the same process, and finally the number of completed process pieces can be counted from the sewing data.

[0067] Similar to the above embodiment principle, the present application provides a sewing equipment automatic piece counting system.

[0068] The following provides specific embodiments in conjunction with the drawings:

[0069] As Figure 7 The structure diagram of a sewing equipment automatic piece counting system in an embodiment of the present application is shown.

[0070] The system comprises:

[0071] The sewing data acquisition module 71 is used to acquire sewing data collected by the sewing equipment; wherein, the sewing data includes: timestamp, stitch count, and sewing status;

[0072] The automatic piece counting module 72 is connected to the sewing data acquisition module 71 and is used to perform automatic piece counting analysis on the sewing data using an automatic piece counting analysis method related to the process complexity of the sewing data, so as to obtain the number of process pieces corresponding to the sewing data; wherein, the types of automatic piece counting analysis methods include: simple sewing process piece counting method and complex sewing process piece counting method.

[0073] It should be noted that, as should be understood Figure 7 The division of modules in the system embodiment is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software through processing element calls; they can be implemented entirely in hardware; or some modules can be implemented through processing element calls in software, while others are implemented in hardware.

[0074] For example, each module can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more digital signal processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together to form a system-on-a-chip (SOC).

[0075] Optionally, the automatic piece counting module 72 includes:

[0076] The simple sewing process piece counting unit 721 is used to automatically analyze and process the sewing data using a simple sewing process piece counting method to obtain the number of process pieces corresponding to the sewing data.

[0077] The piece-rate method for simple sewing processes includes: based on the piece-rate model for simple sewing processes, performing simple sewing process piece-rate analysis on the sewing data to obtain the number of pieces corresponding to the sewing data.

[0078] Optionally, the way of obtaining the number of pieces of the sewing data based on the simple sewing process piece counting model comprises: judging the number of pieces of the sewing data based on the similar needle value and the frequency of each time interval.

[0079] Optionally, the way of judging the number of pieces of the sewing data based on the similar needle value and the frequency of each time interval comprises: grouping the sewing data to obtain one or more data groups; obtaining the time interval between each adjacent data group and the cumulative needle value of each group, and counting the similar needle value and the frequency of each time interval to obtain the convergence time interval and the convergence needle value; and judging the number of pieces of the sewing data based on the convergence time interval and the convergence needle value.

[0080] Optionally, the automatic piece counting module 72 further comprises:

[0081] a complex sewing process piece counting unit 722, configured to automatically count and analyze the sewing data in a complex sewing process piece counting manner to obtain the number of pieces of the sewing data.

[0082] Optionally, the complex sewing process piece counting manner comprises: obtaining the number of pieces of the sewing data based on a complex sewing process piece counting model.

[0083] Optionally, the way of obtaining the number of pieces of the sewing data based on the complex sewing process piece counting model comprises:

[0084] judging the number of pieces of the sewing data based on the standard flow feature data of the corresponding standard process piece marked in the sewing data; wherein the standard flow data comprises: the standard needle value, the standard time stamp and the standard sewing state of each sewing edge.

[0085] Optionally, the method for determining the number of pieces of the sewing data based on the standard process feature data calibrated in the sewing data comprises: determining one or more standard pieces of sewing data in the sewing data to obtain standard process feature data corresponding to one piece; string encoding the sewing data in units of sewing edges according to the standard needle value of each sewing edge; dividing the sewing data into one or more standard data windows and one or more detection data windows based on the standard process feature data; wherein each standard data window corresponds to a standard string encoding segment; each detection data window corresponds to a detection string encoding segment; based on a similarity algorithm, calculating the encoding conversion distance of each detection data window corresponding to the detection string encoding segment and the standard string encoding segment, and taking the number of detection data windows less than the conversion distance threshold as the number of pieces corresponding to the sewing data.

[0086] Optionally, the similarity algorithm adopts a Levenshtein similarity algorithm.

[0087] Optionally, the sewing state comprises one or more of the motor start-stop state, the thread cutting state, and the lifting of the presser foot state.

[0088] In summary, the automatic piece counting method and system of the sewing equipment can automatically analyze and process the collected sewing data by using an automatic piece counting analysis method related to the complexity of the process of the collected sewing data, and obtain the number of pieces corresponding to the sewing data. The present application can select the corresponding automatic piece counting analysis method according to the complexity of the process of the sewing equipment, so as to realize accurate piece counting for sewing data with different process complexities. Therefore, the present application effectively overcomes the various shortcomings in the prior art and has high industrial utilization value.

[0089] The above embodiments only exemplarily illustrate the principles and effects of the present application, and are not intended to limit the present application. Any person skilled in the art can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by those skilled in the art without departing from the spirit and technical thought of the present application should be covered by the claims of the present application.

Claims

1. An automatic piece counting method for a sewing apparatus, characterized by, The method comprises: acquiring sewing data collected by a sewing device; wherein the sewing data comprises: a timestamp, a needle number, and a sewing state; performing automatic piece analysis processing on the sewing data by using an automatic piece analysis mode related to the complexity of the sewing data process, to obtain the piece number corresponding to the sewing data; wherein the type of the automatic piece analysis mode comprises: a simple sewing process piece analysis mode and a complex sewing process piece analysis mode; the automatic piece analysis mode comprises: performing simple sewing process piece analysis processing on the sewing data based on a simple sewing process piece analysis model, to obtain the piece number corresponding to the sewing data; the way of performing simple sewing process piece analysis processing on the sewing data to obtain the piece number corresponding to the sewing data comprises: judging the piece number corresponding to the sewing data based on similar needle number values and the frequency of each time interval identified from the sewing data; the way of judging the piece number corresponding to the sewing data based on similar needle number values and the frequency of each time interval identified from the sewing data comprises: grouping similar data of the sewing data to obtain one or more data groups; acquiring the time interval between each adjacent data group and the cumulative needle number of each group, and counting the frequency of similar needle number values and the frequency of each time interval to obtain a convergence time interval and a convergence needle number value; and judging the piece number corresponding to the sewing data based on the convergence time interval and the convergence needle number value.

2. The automatic part counting method for a sewing apparatus as set forth in claim 1, characterized by, the complex sewing process piece analysis mode comprises: performing complex sewing process piece analysis processing on the sewing data based on a complex sewing process piece analysis model, to obtain the piece number corresponding to the sewing data.

3. The automatic part counting method for a sewing apparatus as set forth in claim 2, characterized by, the way of performing complex sewing process piece analysis processing on the sewing data to obtain the piece number corresponding to the sewing data comprises: judging the piece number corresponding to the sewing data based on the standard process feature data of the corresponding standard process piece marked in the sewing data; wherein the standard process data comprises: a standard needle number value of each sewing edge, a standard timestamp, and a standard sewing state.

4. The automatic part counting method for a sewing apparatus as set forth in claim 3, wherein the way of judging the piece number corresponding to the sewing data based on the standard process feature data marked in the sewing data comprises: determining the sewing data of one or more standard process pieces in the sewing data to obtain the standard process feature data corresponding to one process piece; encoding the sewing data in units of sewing edges according to the standard needle number value of each sewing edge; based on the standard process feature data, dividing the sewing data into one or more standard data windows and one or more detection data windows; wherein each standard data window corresponds to a standard string encoding segment; and each detection data window corresponds to a detection string encoding segment; based on a similarity algorithm, calculating the encoding conversion distance between each detection data window corresponding to the detection string encoding segment and the standard string encoding segment, and taking the number of detection data windows with a conversion distance less than a conversion distance threshold as the piece number corresponding to the sewing data.

5. The automatic part counting method for a sewing apparatus as set forth in claim 4, wherein The similarity algorithm adopts a Levenshtein similarity algorithm.

6. The automatic part counting method for a sewing apparatus as set forth in claim 1, wherein, The sewing state includes one or more of a motor start-stop state, a thread cutting state, and a presser foot lifting state.

7. An automatic piece counting system for a sewing apparatus, comprising: The system includes: a sewing data acquisition module configured to acquire sewing data collected by a sewing device, wherein the sewing data includes a timestamp, a stitch count, and a sewing state; an automatic piece counting module connected to the sewing data acquisition module and configured to perform automatic piece counting analysis on the sewing data using an automatic piece counting analysis method related to a complexity of a sewing process corresponding to the sewing data to obtain a piece count of the sewing process; wherein the automatic piece counting analysis method includes a simple sewing process piece counting method and a complex sewing process piece counting method; the automatic piece counting analysis method includes performing simple sewing process piece counting analysis on the sewing data based on a simple sewing process piece counting model to obtain a piece count of the sewing process corresponding to the sewing data; the method of performing simple sewing process piece counting analysis on the sewing data to obtain a piece count of the sewing process corresponding to the sewing data includes determining a piece count of the sewing process corresponding to the sewing data based on a similar stitch count value identified from the sewing data and a frequency of occurrence of each time interval; the method of determining a piece count of the sewing process corresponding to the sewing data based on a similar stitch count value identified from the sewing data and a frequency of occurrence of each time interval includes grouping similar data from the sewing data to obtain one or more data groups; acquiring a time interval between each adjacent data group and a cumulative stitch count of each group, and counting a similar stitch count value and a frequency of occurrence of each time interval to obtain a convergence time interval and a convergence stitch count value; and determining a piece count of the sewing process corresponding to the sewing data based on the convergence time interval and the convergence stitch count value.

Images