EP1222037B1 - Method and device for sorting parcels - Google Patents

Abstract

The invention relates to sorting items of mail in a plurality of sorting passes. In order not to have to read the address in each sorting pass and also not to have to print any machine-readable identification code on each item of mail, features characteristic of the items of mail are additionally determined during the first sorting pass and are stored together with distribution codes determined in the reading process. During the subsequent sorting passes only the characteristic features of the items of mail are measured and compared with the stored features. In the event of agreement, the item of mail is assigned the associated distribution code. A particular feed regime with defined orders ensures that in each case only n items of mail have to be compared, where n=maximum multiple delivery rate to be expected.

Description

The invention relates to a method for sorting mail items according to the preamble of claim 1 and a device to carry out the procedure.

The main task of shipment sorting systems is that Extract address information on a shipment to this finally to be able to assign a distribution code (recipient). As a rule, the number of possible distribution codes exceeds the number of sorting ends, so that one shipment in several Stages must be sorted, i.e. several times by one Sorting machine is running.

In the first pass, the sorting information from the shipment picture extracted by first an address reading system (OCR) is used. Shipments made by automatic Reading system rejected are manually coded (video coding). The sorting information obtained in the process must for the subsequent sorting processes, in particular to manually reject the rejected consignments and thus coding in subsequent sorting runs have to. As a rule, a code is applied to the shipment, which can simply be read automatically. This contains either the sort information explicitly or represents it a code that uniquely identifies the shipment. In this case, the first time in a database the Code is stored together with the sorting information, so that this in subsequent sorting runs out of the code can be derived from the database.

However, applying this code is not feasible in all mail sorting applications; this is not possible, particularly in applications for sorting in-house mail, since a large part of the items - house mail envelopes - are used several times with different recipient addresses. In this context, a solution for the temporary storage of objects, such as letters or the like. Known in a reading system in which discriminatory features of the objects to be read are additionally determined prior to the intermediate storage and associated with the relevant reading results are stored in a database (DE 40 00 603 C2). When the objects leave the buffer again, the information to be recognized is not read again, but the discriminatory features (so-called fingerprints) are recorded, compared with the stored features and, if the features match a stored feature set, the associated reading result becomes the respective item assigned.
However, the application of this method to real sorting processes is extremely difficult in general, since here a shipment from a very large quantity must be reliably recognized, for example from several 100,000 objects. In addition, in extreme cases, the scanned images of two different letters differ only by a few pixels (if it is Infopost and the addresses differ only in a letter of the first name); on the other hand, 2 images of the same object can differ by significantly more pixels.

The object of the invention is therefore in multi-stage Sorting the repeated reading of the addresses of each Shipment and printing of machine-readable identification codes to avoid by sending the shipments to the following Sort runs if possible by comparing characteristics fewer shipments are identified.

According to the invention, the object is defined in claim 1 and 5 specified teaching solved.

By building a database in which for each shipment next to the read distribution information / distribution code and the Feature sets the order when reading the distribution information and the assigned sorting end number and / or the number of the container in which the shipment in this Sort run is saved is included, it is possible to divide the database into sections assigned to the containers. In the database sections, the data after the Order in reading order. The second or following Sorting will be the items from each container of the previous one Sorting in the order in which they were saved in the container in this or another sorting machine again entered. With the message of the terminal or container number the corresponding database sections are marked, which are necessary for the current identification. Because of the defined and known order of the shipments is then only a comparison of the parameter sets of at least n shipments, n = maximum multiple deduction rate to be expected necessary to the shipments and the distribution code identify. This is done by the parameter set of the first Consignment with the first n parameter sets of the concerned Database section, the parameter set of the second broadcast starting with n parameter sets arranged one after the other compared with the parameter set of the second shipment, etc. becomes. Since only a comparison between a few parameter sets the result is less Effort significantly safer.

Advantageous embodiments of the invention are in the subclaims shown.

Are those belonging to a certain sorting end point with Shipments filled containers not according to their order of filling marked, so is advantageously also the last shipment before or the first shipment after each sorting end emptying marked in the database. To the for the database section applicable to the respective container will then determine the feature set of the first shipment of each Container of this sorting end as long as the first Characteristic records of the assigned to this sorting terminal, in database sections not yet processed in this sorting run compared until a match was found has been.

It is also advantageous, especially when performing the second and further sorting runs on other sorting machines than on the sorting machine of the first sorting run Contents of the database sections in on the relevant containers save attached read-in and read-out memories, before entering the shipments into the sorting machines read out for the second and further sorting runs and in the controls of these sorting machines are entered.

Another advantageous embodiment in this context is the electronic transmission of the relevant database content to those who carry out the second and further sorting processes Sorting machines.

FIG 1

eine schematische Darstellung des Ablaufes beim ersten Sortierlauf

FIG 2

eine schematische Darstellung der folgenden Datenbankbearbeitung

FIG 3

eine schematische Darstellung des Ablaufes beim i-ten Sortierlauf (i>1)

The invention is then explained in more detail in an exemplary embodiment with reference to the drawing.
It shows

FIG. 1

a schematic representation of the process for the first sorting run

FIG 2

a schematic representation of the following database processing

FIG 3

a schematic representation of the process for the i-th sorting run (i> 1)

• den Merkmalssatz/Fingerprint Merkmale
• den Verteilcode
• die Sortierfachnummer j und/oder die Nummer des Behälters 16 zum Zwischenspeichern, in die die Sendung sortiert worden ist
• den Zeitpunkt, zu dem eine Sendung gelesen wurde
• eine Markierung, ob eine Sendung das letzte Objekt in einem Behälter als Zwischenspeicher darstellt

The sorting machine has sorting compartments 14 as the sorting end points, which have to be emptied at a certain filling level.
During the first sorting run, the addresses of the mail items and thus the distribution code are read 11, either automatically by an address reader or manually by video coding personnel. In order to be able to easily access this information in the following sorting runs, a database 12 is built parallel to the reading process and contains mailing data records 13 for characteristic features of all processed mailings. In particular, a shipment data record 13 contains:

• the feature set / fingerprint features
• the distribution code
• the sorting compartment number j and / or the number of the container 16 for intermediate storage, into which the consignment has been sorted
• the time at which a program was read
• a marking whether a shipment represents the last object in a container as a buffer

The first entry is used to re-identify a shipment in subsequent sorting runs, the second entry contains the Distribution code of this shipment. Allow the remaining entries the reduction of the shipment quantity for the subsequent one Re-identification.

• holistische Sendungsmerkmale, wie Höhe, Breite, Grauwertverteilung auf einem abgetasteten Sendungsbild, Lage der Empfängeradresse, etc.
• Merkmale der Empfängeradresse: Anzahl von Zeilen, Anzahl von Wörtern in einer Zeile, Anzahl von Zeichen in einer Zeile, etc.

The fingerprint features take two different aspects into account, firstly properties of mailbox mail and secondly properties of mail from large suppliers. In most cases, letterbox mail can already be distinguished by its geometric dimensions and simple global image features. For large deliverers, the letters differ only in their address, the extent and layout are identical for all items. As a result, two different feature structures are calculated and saved for a shipment:

• holistic consignment characteristics, such as height, width, gray value distribution on a scanned consignment image, location of the recipient's address, etc.
• Characteristics of the recipient address: number of lines, number of words in a line, number of characters in a line, etc.

The sorting machine distributes each consignment supplied to it into a sorting compartment 14. As a rule, the buffer capacity of a sorting compartment 14 is not sufficient for the items to be processed in a sorting run, so that the items have to be temporarily stored in containers 16, for example in trays, before they become one subsequent sorting process can be supplied. When the shipments are reloaded from a sorting compartment 14 into a buffer store 16, the order of the shipments must be maintained. Furthermore, for each container 16, the information must exist with which sorting compartment 14 the mail items that it contains correspond. For example, the correspondence between the container sorting compartment number and a label (plain text or bar code) that is attached to the container. Furthermore, a card can optionally be inserted into each container 16 - at the beginning or at the end (marked with a start in FIG. 1), which can be easily identified automatically in a subsequent sorting run. It is cheap (but not necessary) if the order of the containers (with regard to filling) is known so that this information can be used for the subsequent sorting run.
In addition to the features and the sort code, the point in time at which a consignment was read in the sorting machine and into which sorting compartment 14 and / or which container 16 this consignment was temporarily stored is stored in the database 10. Furthermore, the sorting machine reports via the machine control the time and the sorting compartment number to the database 10 at which this sorting compartment 14 has been emptied 15. This information is, however, only necessary if the order of the containers 16 for intermediate storage for one sorting compartment 14 is not for the following one Sorting can be held.

After a complete sorting run, the database 10 contains all mail items in the chronological order in which they were fed to the sorting machine. The database objects are now re-sorted 21 according to the sorting compartment 14 (primary key) and within a compartment according to the time (secondary key) of reading the distribution address. Furthermore, the database entries of a sorting bin 14 are marked in the element transition 22, the time stamp of which corresponds to the time when a bin content was emptied into a container 16, provided that this information was stored in the first pass. This marking consequently divides the number of mail items in a sorting bin 14 into exactly as many subsets as containers 16 have been created for intermediate storage.
The database 10 is subsequently distributed to the sorting machines on which the mail items are further sorted. It is advantageous not to send the complete database 10, but only the database areas that correspond to the mailings that are processed there.

• Die Reihenfolge der Sortierfachnummern wird vom Steuerrechner über das User-Interface vorgegeben.
• Die Bedienkraft gibt die Nummer über ein Eingabefeld ein.
• Die Nummer wird über einen Barcode (Beizettel des Behälters) mit einer Leseeinheit eingegeben.

In the sorting runs 2 and following (FIG. 3), the mail items from the containers 16 are fed to the sorting machine in a predefined sequence with respect to the sorting compartment number. The sequence of the compartment numbers, and thus the order in which the containers are fed, can be compared in different ways with the order of the data records in the database 10:

• The order of the sorting compartment numbers is specified by the control computer via the user interface.
• The operator enters the number in an input field.
• The number is entered using a barcode (label on the container) with a reading unit.

1. Das Sortierfach j wurde in genau einem Behälter gespeichert.

2. Das Sortierfach j wurde in m Behältern gespeichert. Die Reihenfolge dieser m Behälter entspricht der Reihenfolge ihrer Füllung.

3. Das Sortierfach j wurde in m Behälter gespeichert. Die Reihenfolge dieser m Behälter entspricht nicht der Reihenfolge ihrer Füllung.

The corresponding database group 34 is selected 33 by entering 32 the sorting bin number j. The determination of the database section that corresponds to the mailings of the respective container 16 for the sorting bin j requires a closer look. There are 3 cases:

1. The sorting compartment j was stored in exactly one container.

2. The sorting compartment j was stored in m containers. The order of these m containers corresponds to the order of their filling.

3. Sort bin j was stored in m containers. The order of these m containers does not correspond to the order of their filling.

In the first case, the database section corresponding to this container is identical to the selected database group. In the second case, the order of the consignments supplied also corresponds to the order of the consignments in the database 10.
If the containers 16 are not fed in the original order - the third case - the database section must be determined which corresponds to the content of the current container 16. In this case, the information in the "Transition" field and optionally the start card of each container are used for this sorting compartment. The start card indicates that a new container 16 begins and a corresponding database section must therefore be determined again. Since the "transition" element has divided the number of items in the sorting compartment 14 into as many parts as the containers 16 have been created, the first n = 5 items of each subset that have not yet been processed can be used for the selection , The current shipment must therefore be compared with all of these objects and checked for correspondence. The subset forms the corresponding database section, the starting object of which is fingerprint-identical to the current shipment image.

The distribution code of a shipment to be sorted is via the Fingerprint comparison 35 with the first 5 database entries of the applicable database section determined. With everyone successful correspondence will be from this point onwards next 5 database entries with the next program picture adjusted. The number of selected shipment quantities, in in this case 5, must be greater than the maximum expected Multiple removal rate.

The database 10 is updated in every sorting run Updated 36 if further sorting follows got to. For this purpose, the elements for each processed object "Subject number" and "Time2" with the corresponding new ones Values. The "Transition" element is also deleted and the subject empty record is overwritten if both are in use. Before the database 10 for the following Sorting is sorted 21 u. 22, the Contents of the two fields "Zeitpunk1" and "Zeit2" exchanged 23rd

Saving the fingerprint characteristics and the distribution code can - as an alternative to the proposed central database solution - also take place via electronic memory modules, which are attached directly to the container 16, and so that these data are made available locally the place where they are needed. For example Stickers with semiconductor memories are used after the filling of the container 16 with the information of the fingerprint features and the distribution code loaded and directly to be attached to this container 16. In subsequent sorting runs the contents of the label will be fed into the sorting machine is read out and the fingerprint comparison 35 performed. The start of this is shown on the start card Stack detected.

Claims (5)

1. Method of sorting items of mail by means of sorting machines with sorting endpoints, which comprise sorting bins (14) or replaceable containers (16), in multiple sorting passes, the surface of the item of mail with the distribution address being recorded and the latter read during each first sorting pass,
   characterized in that

   during the first sorting pass, characteristic features of the item of mail and/or features of the address are additionally determined for each item of mail as a set of features for distinguishing at least n items of mail, where n = the maximum multiple delivery rate to be expected,

   when a defined level is reached in each sorting endpoint, the container (16) is changed or the sorting bin (14) is emptied and the items of mail emptied out are stored temporarily in containers (16) while maintaining their order, the containers (16) being identified at least with the sorting endpoint number,

   for each item of mail, the order of reading the distribution address, the associated sorting endpoint number and/or the number of the container (16) in which the item of mail is stored in this sorting pass, the distribution code determined from the address read and the characteristic feature set are stored in a database (10),

   in the second and each further sorting pass, the items of mail from each container (16) from the respective previous sorting pass are put into this or another sorting machine in the order in which they were stored in the container (16), the associated endpoint or container number is reported to the sorting machine and therefore the database section relevant to the respective container (16) is determined, the data in each database section being ordered in accordance with the order of reading the distribution address, for each item of mail the defined characteristic feature set is determined, with the aid of which the respective distribution code is then determined, by the characteristic feature set of the first item of mail being compared with n characteristic feature sets stored one after another in this database section, beginning with the feature set of the first item of mail, and, if there is agreement within a defined range, the associated stored distribution code being assigned to the first item of mail, by the characteristic feature set of the second item of mail being compared with n characteristic feature sets stored one after another in this database section, beginning with the feature set of the second item of mail, and, if there is agreement, the stored distribution code for this feature set being assigned to the second item of mail, and this procedure is repeated until the feature sets of all the items of mail supplied have been compared with the associated stored feature sets.
2. Method according to Claim 1, characterized in that if the order of the containers (16) belonging to a sorting endpoint has not been identified, in order to detect the transition from one container (16) to the other, in addition the respective last item of mail before or the first item of mail after each sorting endpoint emptying is identified in the database (10), and the feature set of the first item of mail of each container (16) of one sorting endpoint in each case is compared with the first n feature sets of the database sections associated with this sorting endpoint but not yet processed in this sorting pass until agreement, and therefore the database section associated with the items of mail in this container (16), have been determined.
3. Method according to Claim 1 or 2, characterized in that the contents of the database sections are stored in memories which are fitted to the relevant containers (16) and which can be written to and read from, said memories being read out before the items of mail are put into the sorting machines for the second and further sorting passes and being put into the control systems of these sorting machines.
4. Method according to Claim 1 or 2, characterized in that the relevant database contents are transmitted electronically to the sorting machines carrying out the second and further sorting passes.
5. Apparatus for implementing the method according to Claim 1.

Images