CN109649916B - Intelligent container cargo identification method and device - Google Patents
Intelligent container cargo identification method and device Download PDFInfo
- Publication number
- CN109649916B CN109649916B CN201811427143.5A CN201811427143A CN109649916B CN 109649916 B CN109649916 B CN 109649916B CN 201811427143 A CN201811427143 A CN 201811427143A CN 109649916 B CN109649916 B CN 109649916B
- Authority
- CN
- China
- Prior art keywords
- goods
- total weight
- standard
- combination
- identified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G1/00—Storing articles, individually or in orderly arrangement, in warehouses or magazines
- B65G1/02—Storage devices
- B65G1/04—Storage devices mechanical
- B65G1/137—Storage devices mechanical with arrangements or automatic control means for selecting which articles are to be removed
- B65G1/1373—Storage devices mechanical with arrangements or automatic control means for selecting which articles are to be removed for fulfilling orders in warehouses
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G1/00—Storing articles, individually or in orderly arrangement, in warehouses or magazines
- B65G1/02—Storage devices
- B65G1/04—Storage devices mechanical
Abstract
The application discloses intelligent container cargo identification method, including: acquiring an actual total weight value of the goods to be identified; acquiring the type and the quantity of the corresponding standard goods; selecting different types and quantities of standard goods to be combined to obtain the standard goods of each combination; calculating the confidence coefficient of each combination according to the actual total weight value of the goods to be identified and the total weight of the standard goods of each combination, and selecting the maximum confidence coefficient; and when the maximum confidence coefficient is greater than a preset threshold value, identifying the goods to be identified as the standard goods of the corresponding combination of the maximum confidence coefficient. By applying the technical scheme disclosed by the application, the goods can be quickly and accurately identified through the change of the weight of the goods.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a method and a device for identifying goods in an intelligent container.
Background
With the development of artificial intelligence technology, the intellectualization of various industries is also silently established. The intelligent container is the product of the artificial intelligence technology. The intelligent container is a product which meets the requirements of customers, provides goods and collects money in an environment without manual intervention. Because the installation is convenient, the time and the place are not limited, and special salesmen are not needed, the method is favored by more and more merchants.
However, the current intelligent container usually isolates the goods from the customers by using a transparent material, and the customers can only select the goods through the keys outside the container and put the goods into the goods taking groove by mechanical transmission inside the container. The speed of identifying the goods through the keys is slow, and the customer experience is poor.
Disclosure of Invention
The application provides an intelligent container cargo identification method which can quickly and accurately identify cargos through cargo weight change. The specific scheme is as follows:
an intelligent container cargo identification method comprises the following steps:
acquiring an actual total weight value of the goods to be identified;
acquiring the type and the quantity of the corresponding standard goods;
selecting different types and quantities of standard goods to be combined to obtain the standard goods of each combination;
calculating the confidence coefficient of each combination according to the actual total weight value of the goods to be identified and the total weight of the standard goods of each combination, and selecting the maximum confidence coefficient;
and when the maximum confidence coefficient is greater than a preset threshold value, identifying the goods to be identified as the standard goods of the corresponding combination of the maximum confidence coefficient.
Further, the method for calculating the confidence of each combination according to the actual total weight value of the goods to be identified and the standard total weight of the goods of each combination comprises the following steps:
for each combination, calculating the absolute value of the difference between the actual total weight value of the goods to be identified and the total weight of the standard goods of the combination;
obtaining a matching rate according to a preset maximum difference value and the absolute value of the difference value;
and obtaining the confidence coefficient of the combination according to the matching rate and a preset weight corresponding to the combination.
Further, the method further comprises:
and when the maximum confidence coefficient is not greater than a preset threshold value, returning the information of the failure of the identification of the goods to be identified.
Further, the air conditioner is provided with a fan,
the method for acquiring the actual total weight value of the goods to be identified comprises the following steps: when the goods are taken out, acquiring an actual total weight value of the goods to be identified according to a difference value between the total weight of the original goods and the total weight of the remaining goods;
the method for acquiring the type and the quantity of the corresponding standard goods comprises the following steps: and acquiring the type and the quantity of the owned standard goods from the existing current goods channel record.
The method further comprises the following steps:
and when the maximum confidence coefficient is not greater than a preset threshold value, returning the information of placing abnormal articles in the goods channel.
Further, the air conditioner is provided with a fan,
the method for acquiring the actual total weight value of the goods to be identified comprises the following steps: when the goods are put back, acquiring the actual total weight value of the goods to be identified according to the difference value between the original total weight of the goods and the latest total weight of the goods;
the method for acquiring the type and the quantity of the corresponding standard goods comprises the following steps: the type and quantity of the owned standard goods are obtained from the shopping cart records.
The embodiment of this application scheme still provides an intelligence packing cupboard goods recognition device, and the device includes:
the first acquisition unit is used for acquiring the actual total weight value of the goods to be identified;
the second acquisition unit is used for acquiring the type and the quantity of the corresponding standard goods;
the combination unit is used for selecting different types and quantities of standard goods to be combined to obtain the standard goods of each combination;
the confidence coefficient calculation unit is used for calculating the confidence coefficient of each combination according to the actual total weight value of the goods to be identified and the total weight of the standard goods of each combination, and selecting the maximum confidence coefficient;
and the identification unit is used for identifying the goods to be identified as the standard goods correspondingly combined with the maximum confidence coefficient when the maximum confidence coefficient is greater than a preset threshold value.
Further, the confidence calculation unit includes:
the matching rate calculation unit is used for calculating the absolute value of the difference value between the actual total weight value of the goods to be identified and the total weight of the standard goods of the combination for each combination; obtaining a matching rate according to a preset maximum difference value and the absolute value of the difference value;
and the weighting calculation unit is used for obtaining the confidence coefficient of the combination according to the matching rate and the preset weight value corresponding to the combination.
An embodiment of the present application further provides a computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the steps of the intelligent container cargo identification method described above.
The embodiment of the application also provides an intelligent container, which at least comprises the computer-readable storage medium and a processor capable of executing the instructions in the computer-readable storage medium.
According to the technical scheme, the maximum confidence coefficient is obtained through calculation according to the actual total weight value of the goods to be recognized and the total weight of the standard goods of each combination, and when the maximum confidence coefficient is larger than a preset threshold value, the goods to be recognized are recognized as the standard goods of the combination corresponding to the maximum confidence coefficient. Because this application embodiment can discern the goods through the change of goods weight, avoid mechanical button, can discern the goods fast accurately.
Drawings
FIG. 1 is a schematic diagram of an intelligent container to which the method of the embodiment of the present application is applied.
Fig. 2 is a flowchart of a method according to a first embodiment of the present application.
Fig. 3 is a schematic structural diagram of an apparatus corresponding to a method according to an embodiment of the present disclosure.
Fig. 4 is a flowchart of a method according to a second embodiment of the present application.
Fig. 5 is a flowchart of a method according to a third embodiment of the present application.
Fig. 6 is a schematic diagram of the internal structure of confidence level calculating unit L4 in fig. 3 of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described in detail below by referring to the accompanying drawings and examples.
FIG. 1 is a schematic diagram of an intelligent container to which the method of the embodiment of the present application is applied. As shown in FIG. 1, the intelligent container comprises a plurality of cargo channels, and the cargo channels are used for carrying cargo to be sold. Below each lane is a scale, such as an electronic scale, for weighing. The results of the electronic weighing are fed back to the processor part of the intelligent container in real time. The weight fed back by the processor part is calculated according to the scheme of the embodiment of the application, and the goods are quickly identified according to the change of the weight.
Fig. 2 is a flow chart of a method according to an embodiment of the present application. As shown in fig. 1, when the weight of each lane is changed, the goods causing the weight change can be identified as follows. The method comprises the following steps:
step S1: and acquiring the actual total weight value of the goods to be identified.
In practical applications, the weight of the goods in one lane may change when the customer takes the goods from the intelligent container or when the customer returns the goods from the shopping cart. In either case, the weight of the goods in the goods way is changed, and the change is the actual total weight value of the goods to be identified.
Step S2: and acquiring the type and the quantity of the corresponding standard goods.
The intelligent container can sell a plurality of goods simultaneously, and each goods way can bear the goods of different kinds and quantity. Typically, each item is produced in accordance with standard specifications, such as various individually packaged food items, which are subject to uniform standards of size and weight. The standard goods mentioned here are goods of standard specification. The standard size cargo has a standard weight. And the actual goods sold are in error in weight from the standard goods.
Before and during the selling process of each goods channel, the goods channels bear which kinds of goods, and the weight of the standard goods corresponding to each kind of goods can be recorded. In addition, when the customer takes away to obtain the goods placed in the shopping cart, the types and the quantity of the goods in the shopping cart can be recorded.
Step S3: and selecting different types and quantities of standard goods to be combined to obtain the standard goods of each combination.
Step S4: and calculating the confidence coefficient of each combination according to the actual total weight value of the goods to be identified and the total weight of the standard goods of each combination, and selecting the maximum confidence coefficient.
Here, the confidence level is the confidence level, or the degree of match between the goods to be identified and the combined standard goods. The greater the confidence, the greater the likelihood of the item to be identified being the combination and vice versa.
Step S5: and when the maximum confidence coefficient is greater than a preset threshold value, identifying the goods to be identified as the standard goods of the corresponding combination of the maximum confidence coefficient.
Fig. 3 is a schematic diagram of an apparatus corresponding to a method according to an embodiment of the present disclosure. As shown in fig. 3, the apparatus includes: a first acquisition unit L1, a second acquisition unit L2, a combination unit L3, a confidence level calculation unit L4, and a recognition unit L5. The first obtaining unit L1 is configured to obtain an actual total weight value of the cargo to be identified. The second acquiring unit L2 is used to acquire the kind and number of the corresponding standard goods. The combination unit L3 is used to select different kinds and numbers of standard goods to be combined, and obtain standard goods of each combination. The confidence coefficient calculation unit L4 is configured to calculate a confidence coefficient of each combination according to the actual total weight value of the cargo to be identified and the total weight of the standard cargo of each combination, and select a maximum confidence coefficient. The identifying unit L5 is configured to identify the good to be identified as the standard good of the corresponding combination of the maximum confidence degrees when the maximum confidence degree is greater than the preset threshold value.
That is to say, in the embodiment of the present application, the actual total weight value of the goods to be identified is obtained first, and then the type and the number of the standard goods are obtained from the record. Combining different kinds and quantities of standard goods to obtain combined weight, and finding out one combination with the highest confidence. If the maximum confidence is larger than the threshold, the goods to be identified is the goods corresponding to the combination which can be trusted.
As mentioned above, in practical applications, the weight of the goods in a lane may change when the customer takes the goods from the intelligent container or when the customer returns the goods from the shopping cart. These two cases are exemplified separately below.
Fig. 4 is a flowchart of the method of the second embodiment. Suppose that the second embodiment is that the weight of a certain goods channel changes when a customer takes goods from the goods channel. As shown in fig. 4, the method includes:
step M1: and when the goods are taken out, acquiring the actual total weight value of the goods to be identified according to the difference value between the total weight of the original goods and the total weight of the residual goods.
In practical application, the current cargo weight of each cargo channel can be recorded in real time. The weight of the lane has been recorded with an initial value before the customer takes the goods. After the customer takes the goods away, the electronic scale under the goods way can weigh the weight of the current remaining goods immediately, and then the difference value is the actual total weight value of the goods to be identified which are taken away.
Step M2: and acquiring the type and the quantity of the owned standard goods from the current goods channel record.
When the weight of a certain goods channel changes, the type and the quantity of standard goods owned by the goods channel can be inquired from the corresponding goods channel record. For example, a lane record may be represented as follows:
watch 1
The goods channel 1 bears three kinds of goods, namely 8 goods A, 5 goods B and 7 goods C; the goods way 2 bears three kinds of goods, the goods D have 4, the goods E have 5, and the goods F have 2. The type and the number of the goods carried by each goods channel are not limited, and are determined by the carrying space of the intelligent container and the requirement on the calculation speed. Usually, the container space is large, and the types and the number of the goods that can be carried by each goods way are also large, but the calculation of the subsequent combination calculation will increase.
Step M3: and selecting different types and quantities of standard goods to be combined to obtain the standard goods of each combination.
The kinds and the number of the standard goods are obtained from the step M2, and the goods can be completely combined. Taking lane 1 as an example, these goods may be combined as follows: combination 1: 1 cargo a +1 cargo B +1 cargo C; and (3) combination 2: 3 goods A; and (3) combination: in summary, 2 items A +1 item B … …, various combinations can be obtained by this step.
Step M4: for each combination, calculating the absolute value of the difference between the actual total weight value of the goods to be identified and the total weight of the standard goods of the combination.
After obtaining the various combinations from step M3, the weights of the combinations can be calculated directly. In practical application, the standard weight of each cargo can be recorded, and the method is shown in table two:
watch two
Assuming that the actual total weight W of the cargo to be identified is 300 g, and a combination is 1 cargo a +1 cargo B +1 cargo C, the step may calculate to obtain a combined standard total weight W of 100+50+ 80-230 g. Then the absolute value of the difference between the actual total weight value of the goods to be identified and the combined standard total weight of the goods is 300-.
Step M5: and obtaining the matching rate according to the preset maximum difference and the absolute value of the difference.
This embodiment may set a maximum difference value based on empirical values. Because in practical applications, since the actual goods are produced according to standard goods, the error from the standard weight should not be too large, although not necessarily the standard weight. Assuming that the maximum difference a is set to 100 grams here based on empirical values, the matching ratio p can be expressed as:
p＝(100-|300-(100+50+80)|)/100＝0.7
step M6: and obtaining the confidence coefficient of the combination according to the matching rate and a preset weight corresponding to the combination.
In practical application, different weights b can be set for different combinations according to empirical values. For example, after the matching rate is calculated in step M5, p × b is used, and the result is used as the confidence. In practical application, when setting the weight b, the following may be considered: the weight of the combination of a single cargo type can be greater than the weight of the combination of multiple cargos, and the weight of the cargos owned by the original cargo channel can be greater than the weight of the cargos owned by the non-original cargo channel. It can be assumed that the weight corresponding to the combination of 1 cargo a +1 cargo B +1 cargo C is set to 5 in advance, and the confidence calculated in the step should be 0.7 × 5 — 3.5.
The steps M4 to M6 are actually a specific method how to calculate the confidence of each combination according to the actual total weight value of the goods to be identified and the total weight of the standard goods of each combination, that is, the specific implementation method of the step S4 in the embodiment may be represented by the following formula: b (A-W-W/A). Wherein, A represents the maximum difference value, W represents the actual total weight value of the goods, W represents the total weight of the standard goods, and b represents the combined weight. The confidence levels of the various combinations obtained in step M3 can be calculated in this way. Of course, in practical applications, the confidence level may not be calculated according to the above method, as long as the degree of matching between the actual total weight value of the goods to be identified and the combined total weight of the standard goods can be expressed, and this is not taken as a limitation of the protection scope of the present application.
Step M7: the calculated maximum confidence is selected.
Step M8: judging whether the maximum confidence coefficient is greater than a preset threshold value, and if so, executing a step M9; otherwise, step M10 is performed.
Step M9: and identifying the goods to be identified as the standard goods correspondingly combined with the maximum confidence coefficient, and ending.
Step M10: and returning the information of failed identification of the goods to be identified, and ending. In this step, if the maximum confidence calculated according to the combination does not reach the threshold, it indicates that the goods in the lane may not be placed in a preset manner, and there may be other goods that do not belong to the lane, and settlement cannot be performed, so that an alarm is given as an identification failure.
By applying the scheme of the embodiment, when a customer takes out goods from a certain goods channel of the intelligent container and puts the goods into a shopping cart, the goods taken by the customer can be identified according to the weight change by using the scheme of the second embodiment. The purpose of goods identification is to automatically settle accounts subsequently, so that an artificial intelligent shopping mode without a shopping guide and a cashier is completely realized.
Fig. 5 is a flowchart of the method of the third embodiment. Suppose that the third embodiment is that the weight of the goods channel changes when the customer returns the goods from the shopping cart. As shown in fig. 5, the method includes:
step N1: and when the goods are returned, acquiring the actual total weight value of the goods to be identified according to the difference value between the original total weight of the goods and the latest total weight of the goods.
In practical application, the current cargo weight of each cargo channel can be recorded in real time. After the customer removes the goods, the weight of the goods channel is recorded with an initial value. When the customer returns the goods, the electronic scale under the goods channel can immediately weigh the current weight of the goods, and then the difference value is the actual total weight value of the returned goods to be identified.
Step N2: and acquiring the type and quantity of the owned standard goods from the current shopping cart record.
When the weight of a certain goods channel changes due to returned goods, the type and the quantity of the standard goods owned by the shopping cart can be inquired from the corresponding shopping cart record. For example, the existing records of the shopping cart can be expressed as follows:
watch III
Wherein, there are two kinds of goods in the shopping cart, goods A has 1, goods C has 2
Step N3: and selecting different types and quantities of standard goods to be combined to obtain the standard goods of each combination.
The kinds and the number of the standard goods obtained from the step N2 can be completely combined. Taking table three as an example, these goods may be combined as follows: combination 1: 1 cargo A; and (3) combination 2: 1 cargo C; and (3) combination: 2 goods C; and (4) combination: in summary, 1 cargo a +2 cargo C … … can be combined in various ways through this step.
Step N4: for each combination, calculating the absolute value of the difference between the actual total weight value of the goods to be identified and the total weight of the standard goods of the combination.
After obtaining the various combinations from step N3, the weights of the combinations can be directly calculated. In practice, the standard weight of each cargo can be recorded, and the method is still as shown in table two.
Assuming that the actual total weight W of the cargo to be identified is 79 g, and the combination 1 is 1 cargo a, the step may calculate that the standard total weight W of the combination is 100 g. Then the absolute value of the difference between the actual total weight value of the goods to be identified and the combined standard total weight of goods is 21 grams from 79 to 100. Similarly, the absolute value of the difference between the actual total weight value of the goods to be identified calculated by the combination 2 and the total weight of the standard goods of the combination is |79-80|, which is 1 g.
Step N5: and obtaining the matching rate according to the preset maximum difference and the absolute value of the difference.
This embodiment may set a maximum difference value based on empirical values. Because in practical applications, since the actual goods are produced according to standard goods, the error from the standard weight should not be too large, although not necessarily the standard weight. Assuming that the maximum difference a is set to 100 grams here based on empirical values, the matching ratio p for combination 1 can be calculated as: p ═ (100- |79-100|)/100 ═ 0.79. The matching rate p for combination 2 can be calculated as: p ═ (100- |79-80|)/100 ═ 0.99
Step N6: and obtaining the confidence coefficient of the combination according to the matching rate and a preset weight corresponding to the combination.
In practical application, different weights b can be set for different combinations according to experience. For example, after the matching rate is calculated in step M5, p × b is used, and the result is used as the confidence. Assuming that the weight corresponding to the combination of 1 item a is set to 5 in advance, and the weight corresponding to the combination of 1 item C is also set to 5 in advance, the confidence calculated for the combination 1 should be 0.79 × 5 to 3.95, and the confidence calculated for the combination 2 may be 0.99 × 5 to 4.95.
Steps N4 to N6 are actually specific methods how to calculate the confidence of each combination according to the actual total weight value of the goods to be identified and the total weight of the standard goods of each combination, that is, the specific implementation method of step S4 in the embodiment may be represented by the following formula: b (A-W-W/A). Wherein, A represents the maximum difference value, W represents the actual total weight value of the goods, W represents the total weight of the standard goods, and b represents the combined weight. The confidence levels of the various combinations obtained in step N3 can be calculated in this way. Of course, in practical applications, the confidence level may not be calculated according to the above method, as long as the degree of matching between the actual total weight value of the goods to be identified and the combined total weight of the standard goods can be expressed, and this is not taken as a limitation of the protection scope of the present application.
Step N7: the calculated maximum confidence is selected.
In the above example, the confidence of combination 1 is 3.95, and the confidence of combination 2 is 4.95, and it is assumed that this step selects the confidence corresponding to combination 2.
Step N8: judging whether the maximum confidence coefficient is greater than a preset threshold value, and if so, executing a step M9; otherwise, step M10 is performed.
Step N9: and identifying the goods to be identified as the standard goods correspondingly combined with the maximum confidence coefficient, and ending.
Since the maximum confidence corresponds to combination 2, the cargo to be identified is identified as the standard cargo in combination 2, i.e., 1 cargo C. Thereafter, the lane record may be updated based on the returned goods for use by the next subsequent customer for purchase. Accordingly, the shopping cart record can be updated, and returned goods can be deleted from the shopping cart record for subsequent correct settlement.
Step N10: and returning the information that the goods to be identified are abnormal goods, and ending. In this step, if the maximum confidence calculated from the combination does not reach the threshold, it indicates that the returned goods may not be placed in a preset manner, and the lane may be misplaced, thereby alarming as an abnormal goods.
By applying the scheme of the third embodiment, when the customer returns the goods from the shopping cart to the intelligent container, the goods returned by the customer can be identified according to the weight change by using the scheme of the third embodiment.
The steps M4 to M6 in the second embodiment and the steps N4 to N6 in the third embodiment provide specific methods for calculating the confidence of each combination according to the actual total weight of the goods to be identified and the standard total weight of the goods in each combination, and the same methods can be used. Fig. 6 is a schematic structural diagram of an apparatus corresponding to this method, that is, a schematic internal structural diagram of confidence level calculating unit L4 in fig. 3. As shown in fig. 6, the apparatus includes: a matching rate calculation unit L41 and a weight calculation unit L42. Wherein, the matching rate calculating unit L41 is configured to calculate, for each combination, an absolute value of a difference between the actual total weight value of the cargo to be identified and the total weight of the standard cargo of the combination; and obtaining the matching rate according to the preset maximum difference and the absolute value of the difference. The weighting calculation unit L42 is configured to obtain a confidence of the combination according to the matching rate and a preset weight corresponding to the combination.
In practical application, when the intelligent container sells goods and needs to be supplemented, the staff can place the goods to be supplemented in the corresponding goods channel. And (3) because new goods are put into a certain goods channel, the total weight of the goods in the goods channel changes, and the total weight value of the goods to be identified is calculated. At the moment, the total weight value of the goods to be identified/the standard weight of the goods owned by the goods channel is used for obtaining the quantity of the placed goods, and the goods channel record is updated.
In addition, in practical application, since the actual weight of the goods is different from the weight of the standard specification, the actual weight of the goods, namely the actual weight of the goods in the shopping cart, is recorded when the goods are taken out by using the second embodiment. Thus, when the customer returns certain items, the actual items in the shopping cart are selected for combination in step N3, and the actual weight value of each combination is obtained. The confidence calculation of each combination is carried out by utilizing the actual weight of the goods in the shopping cart in the subsequent steps N4-N6, so that the error can be reduced, and the recognition effect is more accurate.
The method of the embodiments of the present application may be a series of computer instructions, which are stored in a computer-readable storage medium, such as ROM, RAM, EPROM, SD card, SM card, mobile hard disk, etc., and the instructions stored in the computer-readable storage medium may be executed by a processor of the intelligent container to achieve the purpose of identifying the goods.
There is then such an intelligent container in practical use. The intelligent container comprises a plurality of cargo ways, and each cargo way is provided with a device capable of weighing, such as an electronic scale. The intelligent container also includes a computer readable storage medium and a processor that can execute instructions stored in the computer readable storage medium for the purpose of identifying the cargo.
Therefore, the goods are identified by the weight change of the goods, the speed is very high in the whole scheme which is executed by the processor according to the instruction, the goods are determined to be better, fast and convenient compared with the existing mode of determining the goods by using mechanical keys, and the user experience is very good.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (8)
1. An intelligent container cargo identification method is characterized by comprising the following steps:
acquiring an actual total weight value of the goods to be identified;
acquiring the type and the quantity of the corresponding standard goods;
selecting different types and quantities of standard goods to be combined to obtain the standard goods of each combination;
calculating the confidence coefficient of each combination according to the actual total weight value of the goods to be identified and the total weight of the standard goods of each combination, and selecting the maximum confidence coefficient; the formula for calculating the confidence of each combination is as follows: b (A-W-W/A), wherein A represents the maximum difference value, W represents the actual total weight value of the goods, W represents the total weight of the standard goods, and b represents the combined weight;
and when the maximum confidence coefficient is greater than a preset threshold value, identifying the goods to be identified as the standard goods of the corresponding combination of the maximum confidence coefficient.
2. The method of claim 1, further comprising:
and when the maximum confidence coefficient is not greater than a preset threshold value, returning the information of the failure of the identification of the goods to be identified.
3. The method of claim 2,
the method for acquiring the actual total weight value of the goods to be identified comprises the following steps: when the goods are taken out, acquiring an actual total weight value of the goods to be identified according to a difference value between the total weight of the original goods and the total weight of the remaining goods;
the method for acquiring the type and the quantity of the corresponding standard goods comprises the following steps: and acquiring the type and the quantity of the owned standard goods from the existing current goods channel record.
4. The method of claim 1, further comprising:
and when the maximum confidence coefficient is not greater than a preset threshold value, returning the information of placing abnormal articles in the goods channel.
5. The method of claim 4,
the method for acquiring the actual total weight value of the goods to be identified comprises the following steps: when the goods are put back, acquiring the actual total weight value of the goods to be identified according to the difference value between the original total weight of the goods and the latest total weight of the goods;
the method for acquiring the type and the quantity of the corresponding standard goods comprises the following steps: the type and quantity of the owned standard goods are obtained from the shopping cart records.
6. An intelligent container cargo identification device, the device comprising:
the first acquisition unit is used for acquiring the actual total weight value of the goods to be identified;
the second acquisition unit is used for acquiring the type and the quantity of the corresponding standard goods;
the combination unit is used for selecting different types and quantities of standard goods to be combined to obtain the standard goods of each combination;
the confidence coefficient calculation unit is used for calculating the confidence coefficient of each combination according to the actual total weight value of the goods to be identified and the total weight of the standard goods of each combination, and selecting the maximum confidence coefficient; the formula for calculating the confidence of each combination is as follows: b (A-W-W/A), wherein A represents the maximum difference value, W represents the actual total weight value of the goods, W represents the total weight of the standard goods, and b represents the combined weight;
and the identification unit is used for identifying the goods to be identified as the standard goods correspondingly combined with the maximum confidence coefficient when the maximum confidence coefficient is greater than a preset threshold value.
7. A computer readable storage medium storing instructions, characterized in that the instructions, when executed by a processor, cause the processor to perform the steps of the intelligent container freight identification method according to any one of claims 1 to 5.
8. An intelligent container, comprising at least the computer-readable storage medium of claim 7, and a processor that can execute the instructions in the computer-readable storage medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811427143.5A CN109649916B (en) | 2018-11-27 | 2018-11-27 | Intelligent container cargo identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811427143.5A CN109649916B (en) | 2018-11-27 | 2018-11-27 | Intelligent container cargo identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109649916A CN109649916A (en) | 2019-04-19 |
| CN109649916B true CN109649916B (en) | 2021-01-26 |
Family
ID=66111586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811427143.5A Active CN109649916B (en) | 2018-11-27 | 2018-11-27 | Intelligent container cargo identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109649916B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110307887B (en) * | 2019-07-04 | 2021-01-26 | 四川爱创科技有限公司 | Pure gravity-based commodity identification method applied to intelligent container |
| CN111080900B (en) * | 2019-12-23 | 2022-04-29 | 合肥美的智能科技有限公司 | Container, goods processing method and device, electronic device and readable storage medium |
| CN111127750A (en) * | 2019-12-24 | 2020-05-08 | 西安科技大学 | Commodity displacement identification method based on gravity sensor data |
| CN111144871B (en) * | 2019-12-25 | 2022-10-14 | 创新奇智(合肥)科技有限公司 | Method for correcting image recognition result based on weight information |
| CN112102559B (en) * | 2020-08-13 | 2022-04-19 | 四川虹美智能科技有限公司 | Commodity identification method and device based on gravity sensing |
| CN112348248A (en) * | 2020-11-03 | 2021-02-09 | 北京京东乾石科技有限公司 | Method and device for acquiring commodity layout data, container, equipment and medium |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040254759A1 (en) * | 2003-06-13 | 2004-12-16 | Uwe Kubach | State tracking load storage system |
| FI126245B (en) * | 2005-03-09 | 2016-08-31 | Konecranes Finland Oy | Procedure for placing a palletless goods package on a warehouse shelf and handing it over therefrom and administering the package logistics and equipment for carrying out the procedure |
| JP3153701U (en) * | 2009-07-03 | 2009-09-17 | 株式会社まさご電機 | Beverage vending machine article storage case |
| CN106781017A (en) * | 2017-03-07 | 2017-05-31 | 深圳市楼通宝实业有限公司 | Self-service vending method and system |
| CN207752560U (en) * | 2018-01-26 | 2018-08-21 | 江苏美萃恪斯数字技术有限公司 | Unmanned retail cabinet with monitoring function |
| CN108335406A (en) * | 2018-02-08 | 2018-07-27 | 合肥美的智能科技有限公司 | Self-service equipment and its good selling method and self-service system |
| CN108389315B (en) * | 2018-03-02 | 2021-07-20 | 北京京东尚科信息技术有限公司 | Article identification method and apparatus, and computer-readable storage medium |
| CN108335408B (en) * | 2018-03-02 | 2020-11-03 | 北京京东尚科信息技术有限公司 | Article identification method, device and system for vending machine and storage medium |
| CN108875664B (en) * | 2018-06-27 | 2022-07-05 | 北京京东尚科信息技术有限公司 | Method and device for identifying purchased goods and vending machine |
-
2018
- 2018-11-27 CN CN201811427143.5A patent/CN109649916B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109649916A (en) | 2019-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109649916B (en) | Intelligent container cargo identification method and device | |
| EP4027311A1 (en) | Vision- and gravity sensing-based product identification method, device, and system | |
| WO2006020575A1 (en) | Dynamically classifying items for international delivery | |
| CN110930221B (en) | Abnormal order processing method, storage medium and computer equipment | |
| CN107248052A (en) | A kind of commodity stocks information determines method, apparatus and system | |
| CN111382635B (en) | Commodity category identification method and device and electronic equipment | |
| CN110136129A (en) | A kind of commercial quality detection method, device and storage medium | |
| CN111062660A (en) | Online mall inventory quantity calculation method and device | |
| CN110059991B (en) | Warehouse item selection method, system, electronic device and computer readable medium | |
| CN109685980A (en) | A kind of gravity sensing automatic selling counter commodity arrangement method | |
| WO2013173194A1 (en) | A user recommendation method and device | |
| CN110633929B (en) | Commodity counting method, device and equipment | |
| CN113191789A (en) | Goods distribution method and equipment based on second-hand scene | |
| CN111680941B (en) | Method, device, equipment and storage medium for price-keeping recommendation | |
| CN117194764A (en) | Goods display method, equipment and medium based on multi-platform fusion mall | |
| CN112001664A (en) | Method, device, equipment and storage medium for generating return task | |
| CN115761457A (en) | Commodity identification method and device, electronic equipment and computer readable medium | |
| CN108334522B (en) | Method for determining customs code, and method and system for determining type information | |
| CN110969443A (en) | Complaint event processing method, device, equipment and system | |
| CN112418969B (en) | Commodity matching method, commodity matching device and computer equipment | |
| CN106559225B (en) | The method and apparatus of data calibration | |
| CN113487376A (en) | AI intelligent agricultural batch cloud platform processing system and method | |
| CN109189773B (en) | Data restoration method and device | |
| WO2016018711A1 (en) | Systems and methods for price position sensitivity analysis | |
| CN106920020A (en) | The method of cost accounting and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |