CN113688351A

CN113688351A - Method, device, electronic equipment and readable medium for detecting weight of article

Info

Publication number: CN113688351A
Application number: CN202110899379.4A
Authority: CN
Inventors: 邓博洋
Original assignee: Beijing Missfresh Ecommerce Co Ltd
Current assignee: Beijing Missfresh Ecommerce Co Ltd
Priority date: 2021-08-06
Filing date: 2021-08-06
Publication date: 2021-11-23

Abstract

Embodiments of the present disclosure disclose methods, apparatuses, electronic devices, and readable media for detecting a weight of an item. One embodiment of the method comprises: adopting discrete Fourier transform to the gravity value sequence of the target object to obtain the frequency domain characteristics of the gravity value sequence; adopting continuous wavelet transform to the gravity value sequence to obtain the space and frequency combined characteristics of the gravity value sequence; performing frequency connection processing on the gravity value sequence based on the frequency domain characteristics and the joint characteristics to obtain a frequency connection result; and determining the object weight of the target object based on the frequency connection result. This embodiment has realized the accurate detection to the weight of article under the motion state, has improved the precision that article weight detected.

Description

Method, device, electronic equipment and readable medium for detecting weight of article

Technical Field

Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a method and an apparatus for detecting a weight of an article, an electronic device, and a readable medium.

Background

The article weight detection is a method for detecting the weight of an article by a certain technical means. At present, when the weight of an article is detected, the method generally adopted is as follows: the weight of an item placed on an item weight detecting device is often directly determined by the item weight detecting device (e.g., an electronic scale).

However, when the above-described manner is adopted, there are often technical problems as follows:

when the article is in motion during the measurement, the weight value of the article obtained by a few measurements is often not accurate enough.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose methods, apparatuses, electronic devices and readable media for detecting the weight of an item to solve one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide a method for detecting the weight of an item, the method comprising: adopting discrete Fourier transform to the gravity value sequence of the target object to obtain the frequency domain characteristics of the gravity value sequence; adopting continuous wavelet transform to the gravity value sequence to obtain the space and frequency combined characteristics of the gravity value sequence; performing frequency connection processing on the gravity value sequence based on the frequency domain characteristics and the joint characteristics to obtain a frequency connection result; and determining the object weight of the target object based on the frequency connection result.

In a second aspect, some embodiments of the present disclosure provide an apparatus for detecting the weight of an item, the apparatus comprising: and the discrete Fourier transform unit is configured to perform discrete Fourier transform on the gravity value sequence of the target object to obtain the frequency domain characteristics of the gravity value sequence. And the continuous wavelet transform unit is configured to apply continuous wavelet transform to the gravity value sequence to obtain the space and frequency combined characteristics of the gravity value sequence. And a frequency connection unit configured to perform frequency connection processing on the gravity value sequence based on the frequency domain feature and the joint feature to obtain a frequency connection result. A weight determination unit configured to determine an item weight of the target item based on the frequency connection result.

In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method described in any of the implementations of the first aspect.

In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium on which a computer program is stored, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect.

The above embodiments of the present disclosure have the following beneficial effects: by the method for detecting the weight of the article of some embodiments of the present disclosure, the accuracy of the weight detection of the article is improved. Specifically, the reason why the accuracy of the weight detection of the article is low is that: when the article is in a moving state during the measurement process, the weight value of the article obtained by measuring the article for a few times is often not accurate enough. Based on this, some embodiments of the present disclosure provide a method for detecting the weight of an article, which first uses a discrete fourier transform on a gravity value sequence of a target article to obtain a frequency domain feature of the gravity value sequence. In practical situations, due to the influence of the motion state of the article, the weight values of the articles which are different from the actual weight values often exist in the collected weight values of the articles, and the accuracy of the finally obtained weight of the articles is influenced. For example, when an object is placed onto the object weight detecting device at a constant speed or accelerated speed, there is an error between the measured object weight value and the actual weight value due to the acceleration. Therefore, the frequency domain characteristics of the gravity value sequence are obtained by adopting discrete Fourier transform on the gravity value sequence of the target object, the characteristic extraction on the gravity value sequence is realized, and the weight value influencing the accuracy of the final result is better eliminated through the characteristic extraction. And secondly, adopting continuous wavelet transform to the gravity value sequence to obtain the space and frequency combined characteristics of the gravity value sequence. In practical situations, when the weight of an article is light, the influence of the motion state of the article is large, so that the weight values of the collected articles have large difference, and the accurate actual weight value is difficult to determine. For example, when a lighter article is moving at variable speeds, it is affected more by acceleration and the measured weight values vary greatly. Therefore, the combined characteristics of the gravity value sequence are obtained by adopting continuous wavelet transformation on the gravity value sequence of the target object, the characteristic extraction of a smaller weight value sequence is realized, and a more accurate gravity value is selected as a characteristic value through the characteristic extraction. And then, based on the frequency domain characteristics and the joint characteristics, carrying out frequency connection processing on the gravity value sequence to obtain a frequency connection result. In practical situations, the article weight detection device needs to accurately measure the weight of the article no matter the weight of the article, and it is difficult to measure the weight of the article more accurately by using one of the above methods to obtain the weight value of the article. Therefore, the frequency connection result is obtained by performing frequency connection processing on the gravity value sequence, the characteristic connection of the frequency domain characteristic and the joint characteristic is realized, and the influence of the gravity value with a large error on the final result is better reduced through the characteristic connection. And finally, determining the object weight of the target object based on the frequency connection result. In practical situations, the article weight detecting device determines the weight of the article by measuring gravity. However, the article weight detecting device is affected by the motion state of the article when detecting the weight of the article. The gravity value of the article often cannot clearly reflect the characteristics of the gravity value under the moving state of the article. Making it difficult to discern and screen the more valuable gravity values in the gravity value sequence. Therefore, the object weight of the target object is determined based on the frequency connection result, the frequency connection result is converted, and the object weight is clearly and accurately obtained through conversion. By the method, compared with a method of measuring weight through a gravity value, the method can eliminate the interference of acceleration generated by an object in a motion state to a great extent through gravity value conversion, feature extraction and frequency connection. Therefore, the accuracy of the weight detection of the article is improved.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.

FIG. 1 is a schematic illustration of one application scenario of a method for detecting the weight of an item of some embodiments of the present disclosure;

FIG. 2 is a flow chart of some embodiments of a method for detecting the weight of an item according to the present disclosure;

FIG. 3 is a schematic diagram of a gravity value sequence fitting curve of the present disclosure;

FIG. 4 is a schematic diagram of a Fourier series transform curve of the present disclosure;

FIG. 5 is a schematic diagram of a Fourier transform curve of the present disclosure;

FIG. 6 is a schematic diagram of a discrete Fourier transform curve of the present disclosure;

FIG. 7 is a schematic diagram of a continuous wavelet transform curve of the present disclosure;

FIG. 8 is a flow chart of further embodiments of a method for detecting the weight of an item according to the present disclosure;

FIG. 9 is a schematic diagram of some embodiments of an apparatus for detecting the weight of an item according to the present disclosure;

FIG. 10 is a schematic block diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 is a schematic diagram of one application scenario of a method for detecting the weight of an item of some embodiments of the present disclosure.

In the application scenario of fig. 1, first, the computing device 101 may apply discrete fourier transform to the gravity value sequence 102 of the target object to obtain a frequency domain feature 103 of the gravity value sequence 102; secondly, the computing device 101 may perform continuous wavelet transform on the gravity value sequence 102 to obtain a spatial and frequency joint feature 104 of the gravity value sequence 102; then, the computing device 101 may perform frequency connection processing on the gravity value sequence 102 based on the frequency domain feature 103 and the joint feature 104 to obtain a frequency connection result 105; finally, the computing device 101 may determine an item weight 106 of the target item based on the frequency connection result 105.

The computing device 101 may be hardware or software. When the computing device is hardware, it may be implemented as a distributed cluster composed of multiple servers or terminal devices, or may be implemented as a single server or a single terminal device. When the computing device is embodied as software, it may be installed in the hardware devices enumerated above. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.

It should be understood that the number of computing devices in FIG. 1 is merely illustrative. There may be any number of computing devices, as implementation needs dictate.

With continued reference to fig. 2, a flow 200 of some embodiments of a method for detecting the weight of an item according to the present disclosure is shown. The method for detecting the weight of the article comprises the following steps:

step 201, obtaining the frequency domain characteristics of the gravity value sequence by adopting discrete fourier transform to the gravity value sequence of the target object.

In some embodiments, an executing entity (e.g., the computing device 101 shown in fig. 1) of the method for detecting the weight of an article may obtain the frequency domain features of the sequence of gravity values by applying a discrete fourier transform to the sequence of gravity values of the target article, and may include the following steps:

and step one, performing curve fitting according to each gravity value in the gravity value sequence to generate a gravity value sequence fitting curve corresponding to the target object.

The execution body may perform curve fitting according to each gravity value in the gravity value sequence by a least square method to generate a gravity value sequence fitting curve corresponding to the target object. The gravity value in the gravity value sequence may be a gravity value of the target object acquired at a fixed frequency. For example, the fixed frequency may be 0.1 seconds. The target item may be a "courier package". The target item may be an item in an unmanned container.

As an example, the sequence of gravity values may be [3, 5, 8 ]. As shown in fig. 3, fig. 3 includes the gravity value sequence [3, 5, 8] corresponding to the gravity value sequence fitting curve 301. The coordinate system in which the gravity value series fitting curve 301 is located is a coordinate system in which time is taken as a horizontal axis and gravity is taken as a vertical axis. The horizontal axis is a coordinate axis divided by a scale of 0.1 second. The vertical axis is a coordinate axis divided by 1 n as a scale.

And secondly, performing discrete Fourier transform on each gravity value in the gravity value sequence to generate a gravity value frequency sequence.

The Fourier transform is used for transforming a signal from a time domain to a frequency domain, and further researching the frequency spectrum structure and the change rule of the signal. The discrete fourier transform is a transform that transforms a value of time into a value of frequency in discrete time. The execution body may perform sinusoidal processing on the gravity value sequence to perform discrete fourier transform on each gravity value in the gravity value sequence. The discrete fourier transform may be, but is not limited to, any of the following: fourier series transformation and fourier formula transformation.

As an example, the execution body may substitute the gravity value sequence [3, 5, 8] into a fourier series formula to obtain a gravity value frequency sequence [0.11, 0.15, 0.17 ]. The execution body can also carry out the substitution of the gravity value sequence [3, 5, 8] into a Fourier formula to obtain a gravity value frequency sequence [0.12, 0.16, 0.18 ].

And thirdly, performing curve fitting according to each gravity value frequency in the gravity value frequency sequence to generate a discrete Fourier transform curve corresponding to the target object.

The execution subject may use an analytical expression approximation discrete data method to perform curve fitting according to each frequency value in the gravity value frequency sequence, so as to generate a discrete fourier transform curve corresponding to the target object.

As an example, the execution body may perform curve fitting on the gravity value frequency series [0.11, 0.15, 0.17] to obtain the discrete fourier transform curve. Fig. 4 shows a discrete fourier transform curve 401 corresponding to the gravity frequency series [0.11, 0.15, 0.17 ]. The coordinate system in which the discrete fourier transform curve 401 is located is a coordinate system in which the frequency is the horizontal axis and the gravity is the vertical axis. Wherein the horizontal axis is a coordinate axis divided by taking 0.01 Hz as a scale. The vertical axis is a coordinate axis divided by 1 n as a scale.

As another example, the execution body may perform curve fitting on the gravity value frequency series [0.12, 0.16, 0.18] to obtain the discrete fourier transform curve. Fig. 5 shows a discrete fourier transform curve 501 corresponding to the gravity frequency series [0.12, 0.16, 0.18] in fig. 5. The coordinate system in which the discrete fourier transform curve 501 is located is a coordinate system in which the frequency is the horizontal axis and the gravity is the vertical axis. Wherein the horizontal axis is a coordinate axis divided by taking 0.01 Hz as a scale. The vertical axis is a coordinate axis divided by 1 n as a scale.

And fourthly, extracting characteristic value coordinates corresponding to the gravity value sequence fitting curve and the discrete Fourier transform curve to generate frequency domain characteristics of the gravity value sequence.

Wherein the frequency domain feature comprises at least one feature value coordinate. Wherein a eigenvalue coordinate of the at least one eigenvalue coordinate is a coordinate of a valley point in the gravity series fit curve and the discrete fourier transform curve. The valley point may be a lowest point in a sub-curve corresponding to a concave region in the gravity-value-series fitted curve and the discrete fourier transform curve.

As an example, a discrete fourier transform curve as shown in fig. 6. The coordinate system of the discrete Fourier transform curve is a coordinate system with frequency as a horizontal axis and gravity as a vertical axis. Wherein the horizontal axis is a coordinate axis divided by taking 0.01 Hz as a scale. The vertical axis is a coordinate axis divided by 1 n as a scale. The discrete fourier transform curve includes: a valley point 603, a first coordinate point 604, a second coordinate point 605, a concave section 601, and a sub-curve 602 corresponding to the concave section 601. The first coordinate point 604 and the second coordinate point 605 are coordinate points corresponding to two end points of the sub-curve 602 corresponding to the concave section 601.

And step 202, adopting continuous wavelet transform on the gravity value sequence to obtain the space and frequency combined characteristics of the gravity value sequence.

In some embodiments, the performing body obtains the spatial and frequency joint characteristics of the gravity value sequence by using continuous wavelet transform on the gravity value sequence, and includes the following steps:

in the first step, curve fitting is carried out according to each gravity value in the gravity value sequence to generate a first curve.

The execution body may perform curve fitting by a least square method according to each gravity value in the gravity value sequence to generate the first curve.

And secondly, performing continuous wavelet transform on the first curve to generate a gravity value space frequency sequence.

Wherein the continuous wavelet transform is a transform of transforming a value of at least one first sub-curve included in the first curve into a value of frequency. A first sub-curve of the at least one first sub-curve is a curve obtained by dividing the first curve at regular time intervals.

As an example, the execution subject may determine any endpoint corresponding to each of the at least one first sub-curve as a target point, so as to obtain a target point sequence. For example, the target sequence may be [3, 5, 8 ]. The execution body may process the sequence of object points [3, 5, 8] by a continuous wavelet transform formula to generate a sequence of gravity values spatial frequencies [15, 22, 28 ].

And thirdly, performing curve fitting according to each gravity value space frequency in the gravity value space frequency sequence to generate a continuous wavelet transformation curve corresponding to the target object.

The execution subject may perform curve fitting on each gravity value spatial frequency in the gravity value spatial frequency sequence by a least square method to generate a continuous wavelet transform curve corresponding to the target object.

And fourthly, selecting characteristic points in the continuous wavelet transform curve to generate the combined characteristic.

Wherein the execution body may determine a peak point in the continuous wavelet transform curve as a feature point in the continuous wavelet transform curve to generate the joint feature. Wherein the joint feature is composed of at least one feature point.

As an example, a schematic diagram of a continuous wavelet transform curve as shown in fig. 7. The coordinate system of the continuous wavelet transformation curve is a coordinate system with time as a horizontal axis and frequency as a vertical axis. The horizontal axis is a coordinate axis divided by a scale of 0.5 seconds. The vertical axis is a coordinate axis divided by 4 Hz. The continuous wavelet transform curve shown in fig. 7 may include: a first peak point 701, a second peak point 702, and a third peak point 703. The coordinates corresponding to the first peak point 701 may be (1.0, 15), the coordinates corresponding to the second peak point 702 may be (2.5, 22), and the coordinates corresponding to the third peak point 703 may be (4.5, 28). The coordinates of the feature point corresponding to the first peak point 701 may be (1.0, 15). The coordinates of the feature point corresponding to the second peak point 702 may be (2.5, 22), and the coordinates of the feature point corresponding to the third peak point 703 may be (4.5, 28). The above-mentioned combination of characteristics may be [ (1.0, 15), (2.5, 22), (4.5, 28) ].

And 203, performing frequency connection processing on the gravity value sequence based on the frequency domain characteristics and the joint characteristics to obtain a frequency connection result.

In some embodiments, the performing body may perform a frequency concatenation process on the gravity value sequence based on the frequency domain feature and the joint feature to obtain a frequency concatenation result, and may include:

firstly, extracting the frequency domain characteristics and the joint characteristics to generate a target characteristic sequence.

As an example, the frequency domain feature may be [ (1, 2), (2, 2), (3, 2) ]. The above-mentioned combination of features may be [ (4, 2), (5, 2) ]. The execution body may combine an abscissa in each coordinate included in the frequency domain feature and an abscissa in each coordinate included in the joint feature to generate the target feature sequence. For example, the target signature sequence may be [1, 2, 3, 4, 5 ].

And secondly, performing weighted summation processing on each target feature in the target feature sequence to generate the frequency connection result.

And determining the weight corresponding to the target feature in the target feature sequence according to the number of the target features in the target feature sequence. The weight corresponding to the target feature in the target feature sequence may be a ratio of 1 to the number of target features in the target feature sequence.

As an example, the target signature sequence may be [1, 2, 3, 4, 5 ]. The weight corresponding to the target feature in the target feature sequence may be 0.2. The calculation process of the weight corresponding to the target feature in the target feature sequence may be as follows: 0.2= 1/5. Wherein, the target signature sequence may be [1, 2, 3, 4, 5] and the corresponding frequency concatenation result may be 3.

And step 204, determining the object weight of the target object based on the frequency connection result.

In some embodiments, the executing agent may query a target database with the frequency connection result as a key to obtain the item weight of the target item. Wherein the target database is a database storing relationship information between frequency connection results and corresponding article weights. And the data in the target database is data corresponding to the relationship information between the frequency connection result and the corresponding article weight obtained by experiments in advance.

For example, the execution agent may Query the target database by using the frequency connection result as a keyword through an SQL (Structured Query Language) statement to obtain the item weight of the target item. The SQL statement may be: SELECT item weight FROM target database WHERE first variable = = frequency connection result. Wherein the frequency connection result may be 0.26. The relationship information of the weight of the article corresponding to the frequency connection result of 0.26 may be (0.26, 10 kg).

With further reference to fig. 8, a flow 800 of further embodiments of methods for detecting the weight of an item is illustrated. The process 800 of the method for detecting the weight of an item includes the steps of:

step 801, obtaining frequency domain characteristics of the gravity value sequence by adopting discrete Fourier transform on the gravity value sequence of the target object.

firstly, transforming each gravity value in the gravity value sequence from a time domain to a frequency domain by using a discrete Fourier formula to generate a gravity value frequency, so as to obtain the gravity value frequency sequence of the target object.

The execution body may perform time-domain to frequency-domain conversion on the gravity value according to a Fast Fourier Transform (FFT) function.

As an example, the sequence of gravity values may be [3, 5, 8 ]. The execution body may transform each gravity value in the gravity value sequence [3, 5, 8] according to the FFT function to generate a frequency sequence [2, 3, 4] corresponding to the gravity value sequence [3, 5, 8 ].

And secondly, determining the gravity value power and the gravity value time domain corresponding to each gravity value in the gravity value sequence to obtain the gravity value power sequence and the gravity value time domain sequence of the target object.

The execution body may perform time-domain to frequency-domain conversion on each gravity value in the gravity value sequence according to pwelch () function. The execution body may further perform a gravity domain to unit time frequency domain transformation on each gravity value in the gravity value sequence according to a pburg () function. The pwelch () function and pburg () function described above may be functions in the pymatlab module corresponding to the Python language.

As an example, the gravity value power sequence may be [150, 250, 400 ]. The time domain sequence of gravity values may be [2.9, 5.1, 8.3 ]. The execution body may transform each gravity value in the gravity value sequence [3, 5, 8] according to the pwelch () function and the pburg () function to generate a gravity value power sequence [150, 250, 400] and a gravity value time domain sequence [2.9, 5.1, 8.3] corresponding to the gravity value sequence [3, 5, 8 ].

And thirdly, performing curve fitting according to each gravity value in the gravity value sequence to generate a gravity value sequence fitting curve corresponding to the target object.

The execution subject may use each gravity value in the gravity value sequence as an input of a curve fitting tool box cftool in MATLAB to generate a gravity value sequence fitting curve corresponding to the target article.

As an example, as shown in fig. 3, fig. 3 includes a gravity value sequence fitting curve 301 corresponding to the gravity value sequence. The coordinate system where the gravity value sequence fitting curve is located is a coordinate system with time as a horizontal axis and gravity as a vertical axis. The horizontal axis is a coordinate axis divided by a scale of 0.1 second. The vertical axis is a coordinate axis divided by 1 n as a scale.

And fourthly, performing curve fitting according to each gravity value frequency in the gravity value frequency sequence to generate a first frequency value fitting curve corresponding to the target object.

The execution subject may use each gravity value frequency in the gravity value frequency sequence as an input of a curve fitting tool box cftool in MATLAB to generate a first frequency value fitting curve corresponding to the target article.

And fifthly, performing curve fitting according to each gravity value power and each gravity value time domain in the gravity value power sequence and the gravity value time domain sequence respectively to generate a second frequency value fitting curve and a time domain value fitting curve corresponding to the target object.

The execution subject may use each gravity value power in the gravity value power sequence and each gravity value time domain in the gravity value time domain sequence as an input of a curve fitting tool box cftool in MATLAB to generate a second frequency value fitting curve and a time domain value fitting curve corresponding to the target article.

Sixthly, respectively determining peak point information corresponding to the gravity value sequence fitting curve, the first frequency value fitting curve, the second frequency value fitting curve and the time domain value fitting curve to generate a sub-frequency domain feature set, and obtaining a sub-frequency domain feature set, wherein the sub-frequency domain features in the sub-frequency domain feature set include: the peak point abscissa and the peak point ordinate.

As an example, the set of sub-frequency domain features obtained by using, as sub-frequency domain features, coordinates (1, 2) corresponding to a peak point a of the gravity value series fit curve, coordinates (2, 2) corresponding to a peak point B of the first frequency value fit curve, coordinates (3, 4) corresponding to a peak point C of the second frequency value fit curve, and coordinates (9, 11) corresponding to a peak point D of the time domain value fit curve may be [ (1, 2), (2, 2), (3, 4), (9, 11) ].

And seventhly, determining the sub-frequency domain feature set as the frequency domain feature.

As an example, the set of sub-frequency domain features [ (1, 2), (2, 2), (3, 4), (9, 11) ] may be the frequency domain features.

And step 802, performing continuous wavelet transform on the gravity value sequence to obtain the space and frequency combined characteristics of the gravity value sequence.

In some embodiments, the performing step of obtaining the spatial and frequency joint characteristics of the gravity value sequence by using continuous wavelet transform on the gravity value sequence may include the following steps:

firstly, dividing a time interval corresponding to the gravity value sequence fitting curve to generate at least one time interval.

Wherein the execution body may divide a horizontal axis of the gravity value series fitting curve by a fixed time to generate at least one time interval. The fixed time may be 0.1 second.

And secondly, performing Fourier transform processing on the fitted curve of the sequence of the sub-gravity values corresponding to each time interval in the at least one time interval to generate a frequency value corresponding to the fitted curve of the sequence of the sub-gravity values, so as to obtain at least one target frequency.

As an example, the execution body may divide the horizontal axis of the gravity value sequence fitting curve a at time intervals of 0.1 second to obtain 20 pieces of sub-gravity value sequence fitting curves with a horizontal axis length of 0.1 second. The fitted curve a of the gravity value series is a curve in which the span of the corresponding two endpoints on the horizontal axis is 2 seconds. The execution body can perform fourier transform on the ordinate 3 of the midpoint of the sub-gravity value sequence fitting curve a, and the frequency value corresponding to the ordinate of the midpoint of the gravity value sequence fitting curve a is 30.

And thirdly, performing curve fitting on each target frequency in the at least one target frequency to generate a target frequency fitting curve.

The executing agent may use each of the at least one target frequency as an input of a curve fitting tool box cftool in MATLAB to generate the target frequency fitting curve.

And fourthly, determining sub-target frequency fitting curves in the target interval in the target frequency fitting curves as the combined characteristics.

The execution body may determine a curve formed by points having ordinate between 8 and 32 in the corresponding coordinates in the target frequency fitting curve as a sub-target frequency fitting curve. The execution subject may determine a set of coordinates corresponding to points in the sub-target frequency fitting curve as the joint feature.

Step 803, determining coordinate information corresponding to the frequency domain feature and the joint feature to generate a coordinate information set, and obtaining at least one coordinate information set.

In some embodiments, coordinate information corresponding to the frequency domain features and the joint features is determined to generate a set of coordinate information, resulting in at least one set of coordinate information.

As an example, the frequency domain feature may be [ (10, 1002), (12, 1002), (14, 1002) ]. The above-mentioned combined feature may be [ (101, 998), (102, 998), (103, 998) ]. The obtained at least one coordinate information set may be { [ (10, 1002), (101, 998) ], [ (12, 1002), (102, 998) ], [ (14, 1002), (103, 998) ] }.

Step 804, determining a coordinate mean value corresponding to each coordinate information group in the at least one coordinate information group to obtain at least one coordinate mean value.

In some embodiments, the execution subject may determine a coordinate mean value corresponding to each of the at least one coordinate information group, and obtain the at least one coordinate mean value. The execution subject may determine a mean value of vertical coordinates in coordinates corresponding to each piece of coordinate information in the coordinate information group as a mean value of coordinates.

As an example, the coordinate information set may be [ (10, 1002), (100, 998) ]. The determined coordinate mean may be 1000.

Step 805, each coordinate mean value in the at least one coordinate mean value is spliced to generate a splicing feature.

In some embodiments, the execution subject may stitch respective ones of the at least one coordinate mean to generate a stitched feature.

As an example, the at least one coordinate mean may be [1001, 1000 ]. The generated stitching feature may be 10011000.

Step 806, inputting the stitching features to a pre-trained target model to generate a frequency connection result.

In some embodiments, the execution agent may input the stitching features to a pre-trained target model to generate the frequency concatenation result. The target model is a model used for determining frequency results corresponding to the splicing features. For example, the target model may include: and (4) fully connecting the layers.

As an example, first, the executing agent may input 10011000 to a pre-trained target model. Therein, the pre-trained target model may convert 10011000 data to [ 0.110010.91000 ], i.e., a probability of 0.1 is 1001 and a probability of 0.9 is 1000. Then, the execution body may select a value 1000 with a high probability as the frequency connection result. The generated frequency concatenation result may be 1000.

In step 807, in response to determining that the frequency connection result is the same as the preset frequency, determining the preset item weight corresponding to the preset frequency as the item weight of the target item.

In some embodiments, the executing body may determine, in response to determining that the frequency connection result is the same as the preset frequency, a preset item weight corresponding to the preset frequency as the item weight of the target item. The execution subject may query a preset frequency table in a target database with the preset frequency as a keyword to obtain the article weight of the target article. The target database is a database storing relationship information between preset frequencies and corresponding article weights. The preset frequency table is a table storing a relationship between a preset frequency and a corresponding article weight.

As an example, the frequency connection result may be 1000, and the execution subject queries the preset frequency table through an SQL statement by using 1000 as a keyword to obtain the weight of the article. The SQL statement may be: the SELECT target database FROM preset frequency table WHERE preset frequency = '1000'. Wherein the above article weight result may be 1 kilogram. The relationship of the weight of the article corresponding to the frequency connection result 1000 may be (1000, 1 kg).

As can be seen in fig. 8, the present disclosure is directed to better enable accurate measurement of the weight of an article as compared to the description of some embodiments corresponding to fig. 2. Firstly, determining coordinate information corresponding to the frequency domain feature and the joint feature to generate a coordinate information group, and obtaining at least one coordinate information group. In practical situations, there may be a large error in determining the frequency domain characteristics of the lighter objects in the moving state, and there may also be a large error in determining the joint characteristics of the heavier objects in the moving state. Therefore, the coordinate information group is generated by determining the coordinate information corresponding to the frequency domain feature and the joint feature, at least one coordinate information group is obtained, and the process of collecting the features of the lighter articles and the heavier articles to the coordinate information group is realized. Through the coordinate information set, the weight of the article can be more completely described. Thus, errors caused by the measurement are reduced. Secondly, determining a coordinate mean value corresponding to each coordinate information group in at least one coordinate information group to obtain at least one coordinate mean value. Then, each coordinate mean of the at least one coordinate mean is stitched to generate a stitching feature. In practical situations, the generated coordinate information set has small errors due to the influence of the motion state of the object. Therefore, the coordinate mean value corresponding to each coordinate information group in the at least one coordinate information group is determined to obtain the at least one coordinate mean value, and the error of the coordinate information group data is reduced. Then, each coordinate mean of the at least one coordinate mean is stitched to generate a stitching feature. And splicing of coordinate mean values with small errors in each coordinate information group is realized. The input to the target model is generated by stitching. And finally, inputting the splicing characteristics into a pre-trained target model to generate a frequency connection result. In practical situations, the object detecting device often determines the weight of the object by measuring gravity. The gravity value of the object under the motion state is easily affected greatly, and errors are caused to cause inaccurate measurement. Therefore, the splicing features are input into the pre-trained target model to generate a frequency connection result, and the purpose of converting the splicing features into the frequency connection result is achieved. Since the frequency of the article is much less affected in the state of motion of the article than the gravity of the article. Therefore, the frequency connection result reflects the real weight of the object more accurately. In this way, compared with a method for measuring gravity through a gravity value, the method for measuring gravity through the gravity value can eliminate the interference of acceleration generated by an object in a motion state to a great extent by generating a coordinate information group, calculating a coordinate mean value, splicing the coordinate mean value and inputting a model. Therefore, the accuracy of the weight detection of the article is improved.

With further reference to fig. 9, as an implementation of the methods illustrated in the above figures, the present disclosure provides some embodiments of an apparatus for detecting the weight of an item, which correspond to those method embodiments illustrated in fig. 2, which may be particularly applicable in various electronic devices.

As shown in fig. 9, an apparatus 900 for detecting the weight of an item of some embodiments includes: a discrete fourier transform unit 901, a continuous wavelet transform unit 902, a frequency connection unit 903, and a weight determination unit 904. The discrete fourier transform unit 901 is configured to perform discrete fourier transform on a gravity value sequence of a target object to obtain frequency domain characteristics of the gravity value sequence; a continuous wavelet transform unit 902 configured to perform continuous wavelet transform on the gravity value sequence to obtain a spatial and frequency combination characteristic of the gravity value sequence; a frequency connection unit 903 configured to perform frequency connection processing on the gravity value sequence based on the frequency domain feature and the joint feature to obtain a frequency connection result; a weight determination unit 904 configured to determine an item weight of the target item based on the frequency connection result.

It will be understood that the elements described in the apparatus 900 correspond to various steps in the method described with reference to fig. 2. Thus, the operations, features, and advantages described above with respect to the method are also applicable to the apparatus 900 and the units included therein, and are not described herein again.

Referring now to FIG. 10, a block diagram of an electronic device (such as computing device 101 shown in FIG. 1) 1000 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 10 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 10, the electronic device 1000 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 1001 that may 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 means 1008 into a Random Access Memory (RAM) 1003. In the RAM 1003, various programs and data necessary for the operation of the electronic apparatus 1000 are also stored. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other by a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.

Generally, the following devices may be connected to the I/O interface 1005: input devices 1006 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 1007 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 1008 including, for example, magnetic tape, hard disk, and the like; and a communication device 1009. The communication device 1009 may allow the electronic device 1000 to communicate with other devices wirelessly or by wire to exchange data. While fig. 10 illustrates an electronic device 1000 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 10 may represent one device or may represent multiple devices as desired.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network through the communication device 1009, or installed from the storage device 1008, or installed from the ROM 1002. The computer program, when executed by the processing apparatus 1001, performs the above-described functions defined in the methods of some embodiments of the present disclosure.

It should be noted that the computer readable medium described in some embodiments of the present disclosure 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 some embodiments of the disclosure, 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 some embodiments of the present disclosure, 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: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: and performing discrete Fourier transform on the gravity value sequence of the target object to obtain the frequency domain characteristics of the gravity value sequence. And adopting continuous wavelet transformation to the gravity value sequence to obtain the space and frequency combined characteristics of the gravity value sequence. And performing frequency connection processing on the gravity value sequence based on the frequency domain characteristics and the joint characteristics to obtain a frequency connection result. And determining the object weight of the target object based on the frequency connection result.

Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. 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 and/or flowchart illustration, and combinations of blocks in the block diagrams and/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 some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, and may be described as: a processor includes a discrete Fourier transform unit, a continuous wavelet transform unit, a frequency connection unit, and a weight determination unit. The names of the units do not limit the units themselves in some cases, for example, the discrete fourier transform unit may also be described as "a unit that applies a discrete fourier transform to the gravity value sequence of the target object to obtain the frequency domain features of the gravity value sequence".

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims

1. A method for detecting the weight of an item, comprising:

adopting discrete Fourier transform to the gravity value sequence of the target object to obtain the frequency domain characteristics of the gravity value sequence;

adopting continuous wavelet transform to the gravity value sequence to obtain the space and frequency combined characteristics of the gravity value sequence;

performing frequency connection processing on the gravity value sequence based on the frequency domain characteristics and the joint characteristics to obtain a frequency connection result;

determining an item weight of the target item based on the frequency connection result.

2. The method of claim 1, wherein the obtaining the frequency domain features of the sequence of gravity values using a discrete fourier transform of the sequence of gravity values of the target item comprises:

transforming each gravity value in the gravity value sequence from a time domain to a frequency domain by using a discrete Fourier formula to generate a gravity value frequency to obtain a gravity value frequency sequence of the target object;

and determining the gravity value power and the gravity value time domain corresponding to each gravity value in the gravity value sequence to obtain the gravity value power sequence and the gravity value time domain sequence of the target object.

3. The method of claim 2, wherein the obtaining the frequency domain features of the sequence of gravity values using a discrete fourier transform on the sequence of gravity values of the target item further comprises:

performing curve fitting according to each gravity value in the gravity value sequence to generate a gravity value sequence fitting curve corresponding to the target object;

performing curve fitting according to each gravity value frequency in the gravity value frequency sequence to generate a first frequency value fitting curve corresponding to the target object;

performing curve fitting according to each gravity value power and each gravity value time domain in the gravity value power sequence and the gravity value time domain sequence respectively to generate a second frequency value fitting curve and a time domain value fitting curve corresponding to the target object;

respectively determining peak point information corresponding to the gravity value sequence fitting curve, the first frequency value fitting curve, the second frequency value fitting curve and the time domain value fitting curve to generate a sub-frequency domain feature to obtain a sub-frequency domain feature set, wherein the sub-frequency domain features in the sub-frequency domain feature set comprise: a peak point abscissa and a peak point ordinate;

and determining the sub-frequency domain feature set as the frequency domain feature.

4. The method according to claim 3, wherein the applying a continuous wavelet transform to the gravity value sequence to obtain the joint features of space and frequency of the gravity value sequence comprises:

dividing a time interval corresponding to the gravity value sequence fitting curve to generate at least one time interval;

and carrying out Fourier transform processing on the fitted curve of the sequence of the sub-gravity values corresponding to each time interval in the at least one time interval to generate a frequency value corresponding to the fitted curve of the sequence of the sub-gravity values, so as to obtain at least one target frequency.

5. The method according to claim 4, wherein the applying a continuous wavelet transform to the gravity value sequence to obtain a spatial and frequency joint feature of the gravity value sequence further comprises:

performing curve fitting on each target frequency in the at least one target frequency to generate a target frequency fitting curve;

and determining sub-target frequency fitting curves in a target interval in the target frequency fitting curves as the combined features.

6. The method of claim 5, wherein the frequency-concatenating the sequence of gravity values based on the frequency-domain feature and the joint feature to obtain a frequency-concatenated result comprises:

determining coordinate information corresponding to the frequency domain feature and the joint feature to generate a coordinate information group to obtain at least one coordinate information group;

determining a coordinate mean value corresponding to each coordinate information group in the at least one coordinate information group to obtain at least one coordinate mean value;

splicing each coordinate mean value in the at least one coordinate mean value to generate a splicing characteristic;

inputting the splicing features into a pre-trained target model to generate the frequency connection result.

7. The method of claim 6, wherein said determining an item weight of said target item based on said frequency connection results comprises:

and in response to the fact that the frequency connection result is the same as a preset frequency, determining a preset article weight corresponding to the preset frequency as the article weight of the target article.

8. An apparatus for detecting the weight of an item, comprising:

the discrete Fourier transform unit is configured to perform discrete Fourier transform on the gravity value sequence of the target object to obtain frequency domain characteristics of the gravity value sequence;

the continuous wavelet transform unit is configured to apply continuous wavelet transform to the gravity value sequence to obtain the space and frequency combined characteristics of the gravity value sequence;

a frequency connection unit configured to perform frequency connection processing on the gravity value sequence based on the frequency domain feature and the joint feature to obtain a frequency connection result;

a weight determination unit configured to determine an item weight of the target item based on the frequency connection result.

9. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon;

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.

10. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1 to 7.