Code reader and computer implemented method for operating the code reader - Patents.com

Abstract

To provide a code reader for reading an optical code and a computer-implemented method for operating the code reader.SOLUTION: A code reader 1 that allows easy access to functions and a secure modification of functions thereof includes: an illumination unit 3 to illuminate a reading area 2 of the code reader; a receiver unit 4 to detect a code from the reading area; an evaluation unit 5 to determine information from the code; and an audio unit 6 to capture acoustic signals from voice of a user. The evaluation unit is trained to carry out a voice learning process in order to learn and store the captured voice as individual voice of an authorized user, so that the voice is stored as personalized voice aV of the authorized user. The evaluation unit is further trained to carry out a voice recognition process in which the personalized voice is recognized as the voice of the authorized user. The evaluation unit is configured to perform a predetermined function only if it is recognized that a call to the predetermined function of the code reader is made by the personalized voice of the authorized user.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The invention relates to a code reader for reading an optical code according to claim 1 and to a computer-implemented method for driving said code reader according to claim 10. [Background technology]

[0002] Such code readers are used in many areas of everyday life to read information data from optical codes, which may be in the form of bar codes, two-dimensional codes (e.g. QR codes, data matrix codes) or other codes (e.g. color codes, dot codes). In this connection, the code reader comprises an illumination unit for exposing the reading field of the code reader or the optical code to light. Furthermore, the code reader comprises a receiving unit serving to receive the light reflected from the optical code, so that the optical code can be detected when it is moved through the reading field of the code reader and from the received light a signal can be generated for determining the information data of the optical code.

[0003] Such code readers are often used, for example, in the retail sector at supermarket checkouts, and in logistics for automatic baggage identification, mail sorting, baggage handling at airports, and other logistics applications.

[0004] When a code reader is activated by a user, or when adaptations need to be made to the code reader, for example because the type of optical code changes or parameters are adapted to the evolution of equipment, a computer with an appropriate connection to the code reader is usually required to appropriately set the new parameters in the code reader and change the settings of the code reader.

[0005] Since code readers are mounted according to the application, for example near conveyor belts or in high-rack warehouses for logistics, easy and unhindered access to the code reader is not always guaranteed.

[0006] Furthermore, if an unauthorized user gains access to the settings of the code reader, the perfect operation of the code reader may be compromised. Summary of the Invention [Problem to be solved by the invention]

[0007] It is therefore an object of the present invention to provide a code reader for reading optical codes, which allows easy and yet secure (in the sense of authorized) access to the device, so that authorized changes can be made to the device. [Means for solving the problem]

[0008] This problem is solved by a code reader having the features of claim 1.

[0009] The code reader for reading optical codes according to the present invention comprises an illumination unit for illuminating a reading area of ​​the code reader, a receiving unit for detecting a code from the reading area, an evaluation unit for determining information of the code, and a voice unit for capturing an acoustic signal of a user's voice, the evaluation unit being configured to perform a voice learning process to learn and store the captured voice as a personal voice of an authorized user, so that the voice is stored as a personalized voice of the authorized user, the evaluation unit being further configured to perform a voice recognition process to recognize the personalized voice as the voice of the authorized user, and further configured to execute a predetermined function of the code reader only if it is recognized that the function has been invoked by the personalized voice of the authorized user.

[0010] Thus, the voice recognition process enables the code reader to uniquely associate an authorized user's personalized voice with predetermined functions, so that only that authorized user can invoke or execute those predetermined functions of the code reader with their own voice.

[0011] In a preferred embodiment, the voice learning process is arranged to learn the authorization of the user by a predefined speech sequence, a password or a fingerprint. In this regard, a microphone or a fingerprint sensor is provided in particular to perform the authorization at the start of the voice learning process. If a correct speech sequence, a correct password or a correct fingerprint is confirmed, the user is identified as an authorized user.

[0012] Furthermore, in particular said predetermined speech sequence is stored in a control device of the code reader and provided for re-recognition or training of the voice of the authorized user by a voice recognition process, which in this context requests the authorized user to repeat the predetermined speech sequence.

[0013] Once the predetermined speech sequence is reproduced by the user, the speech recognition process trains or re-recognizes the user's voice based on the predetermined speech sequence.

[0014] In the case of re-recognition, a comparison is made between the authorized user's stored voice and the captured voice, and if a match is found, the captured voice is recognized as the authorized user's personalized voice and certain functions are permitted for the personalized voice.

[0015] It is advantageous if an artificial intelligence is provided that machine-learns the voice of the authorized user and distinguishes it from other users, in particular unauthorized users, integrated into the voice recognition process and stored in the control device of the code reader, and machine-learns the speech sequences reproduced by the user and associates the authorized user with the trained voice, so that he can be recognized as an authorized user by his voice.

[0016] In another preferred embodiment, the predetermined functions permitted to authorized users include starting or stopping a measurement of the code reader or configuring the code reader.

[0017] It is advantageous if the voice recognition process is arranged to perform a prioritization of the recognized voices and to associate different prioritized code reader functions depending on the voice priorities. This means that a voice associated with an authorized expert can for example enable or disable non-safety-oriented and safety-oriented functions of the code reader. A voice associated with an unauthorized user can only enable or disable for example the function of displaying information of the code reader, but cannot enable or disable a high priority function of setting the code reader.

[0018] It is further preferred if the learned and personalized voice can be stored in a storage device of the code reader and can be transmitted to the evaluation units of other code readers. In particular, the learned and personalized voice can also be stored in a cloud or in a storage device external to the code reader. In this way, it is easy to provide access rights for an authorized user to several code readers of the measurement system by means of his voice, by performing a voice recognition process in one code reader and transmitting the recognized voice of the authorized user to other code readers or by transmitting the voice of the authorized user from the cloud or external storage device to other code readers.

[0019] In a preferred embodiment, the evaluation unit is arranged to audibly or visually indicate to the authorized user whether the execution of the voice recognition process was successful, so that the user immediately knows whether a given function of the code reader (e.g. device settings) is available to him or her.

[0020] Another object of the present invention is to provide a computer-implemented method for operating a code reader that allows easy access to and safe modification of the code reader's functionality.

[0021] This problem is solved according to the invention by a computer-implemented method having the features of independent claim 10.

[0022] A computer implemented method for operating a code reader having a voice unit for capturing an acoustic signal of a user's voice is provided, comprising: Capture a user's speech sequence, learning the voice of an authorized user as a personal voice, storing the voice as a personalized voice, and enabling predetermined functionality of the code reader for authorized users associated with the personalized voice; and Executing the predetermined function when a function invocation is captured by the speech unit as a verbal command using the personalized voice. It includes each step.

[0023] This computer-implemented method allows easy configuration of code readers that are difficult to access due to their operating location, and ensures, among other things, that only the personalized voice of an authorized user activates or deactivates functions permitted for that voice, where permitted functions associated with that voice are, for example, security-oriented functions of the code reader.

[0024] In a preferred embodiment, a predefined speech sequence, a password or a fingerprint is obtained to confirm the authorization of the user and to initiate voice personalization. Advantageously, said voice is machine-learned with artificial intelligence to distinguish between different voices based on learned voice patterns. In this context, a voice recognition process requests the user to reproduce a predefined speech sequence. Once the voice has been recognized and associated with an authorized user, predefined functions authorized for that voice can be enabled or disabled by the voice of the authorized user. In particular, measurement operations or settings of the code reader are initiated or terminated with the personalized voice of the authorized user.

[0025] The computer-implemented method stores the personalized voice of the authorized user as a data set and transmits it to other code readers, which allow the authorized user to perform the predetermined functions of the other code readers, thereby allowing the authorized user to easily access the meshed code readers of the measurement system and, among other things, to perform device settings.

[0026] It is advantageous to distinguish between recognised voices, assign different priorities to them and give the prioritised voices access to certain functions of the code reader, which correspond to them. This means, for example, that safety-related functions of the code reader with a high priority (e.g. device settings) are associated or permitted to the voices of authorised users with a high priority. Non-safety-related functions of the code reader (e.g. displaying information) are permitted or associated to the voices of unauthorised users with a low priority, so that unauthorised users can be reliably excluded from configuring the code reader.

[0027] Preferred configurations and developments and further advantages of the invention can be seen from the dependent claims, the subsequent description and the drawings.

[0028] The present invention will now be described in detail with reference to the drawings, in which: [Brief description of the drawings]

[0029] [Figure 1] FIG. 1 is a schematic perspective view of a measurement system for a belt conveyor. [Diagram 2] 1 is a schematic diagram of a code reader according to the present invention; [Diagram 3] 1 is a schematic diagram of a preferred embodiment of a voice recognition process of a code reader according to the present invention; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0030] 1 shows diagrammatically a belt conveyor F on which parcels P are conveyed in a conveying direction TR indicated by a black arrow, for example to a sorter, not shown. The illustrated application of the belt conveyor F comprises two code readers 1 and 1A, which are arranged close to the belt conveyor F with their respective reading areas 2 and 2A facing towards the belt conveyor F, in order to capture parcels P conveyed through the reading areas 2 and 2A of the code readers 1 and 1A.

[0031] Now, depending on the use case and the settings of each code reader 1 or 1A, the code readers 1 and 1A can obtain the same or different information from the code M attached to the package P for the user N or aN.

[0032] In the application example depicted in Fig. 1, a first code reader 1 arranged at the beginning of a belt conveyor F in the transport direction TR of luggage P detects a code M on an upper surface O. A second code reader 1A arranged behind the first code reader 1 detects a code M on a side surface. Here, the code M is formed as a barcode or a two-dimensional code on the surface of a sticker.

[0033] To provide a reading area 2 or 2A, the code reader 1 or 1A according to the invention comprises an illumination unit 3 for illuminating the reading area 2 or 2A of the code reader 1 or 1A and a receiving unit 4 for detecting the code from the reading area 2 or 2A, as depicted diagrammatically in Figure 2. The information of the code is determined by an evaluation unit 5 of the code reader 1 or 1A.

[0034] According to the invention, a speech unit 6 is provided which acoustically captures the voice V or aV of a user N or aN. The acoustic signal is sent to an evaluation unit 5, which is configured to recognize and store the captured voice V as the personal voice aV of the authorized user aN by performing a speech learning process, so that the voice V is stored as the personalized voice aV of the authorized user aN. In this regard, it is highly advantageous to provide an artificial intelligence which machine-learns the personalized voice aV of the authorized user aN and then distinguishes the personalized voice aV of the authorized user aN from the voices V of other users, in particular unauthorized users N, in a recognition process. The artificial intelligence is preferably stored in the evaluation unit 5.

[0035] After the voice of the authorized user aN has been learned, in a subsequent voice recognition process a voice V can be recognized as the personalized voice aV of the authorized user aN. Once the authorized user aN has been recognized, a certain function of the code reader 1 or 1A is unlocked, i.e. can be invoked or executed, but only if the verbal command corresponding to this function is also issued by said authorized user aN. Thus, not only is the unlocking of the function on a user basis, but the actual invocation (with execution) of the function is performed exclusively for the authorized user aN.

[0036] In particular, the functions permitted for an authorized user aN may include starting or stopping measurements of the code reader 1 or 1A or configuring the code reader 1 or 1A.

[0037] In other words, the voice recognition process allows the authorized user aN to first access the settings of the code reader 1 or 1A by means of verbal commands, since the voice recognition process has allowed the configuration functions of the code reader 1 or 1A in association with the personalized voice aV of the authorized user aN. On the other hand, the voice recognition process also allows the authorized execution of verbal commands for specific functions. In addition, the verbal commands may allow the authorized user aN to activate or deactivate hardware elements of the code reader 1 or 1A, where the hardware elements include for example the keyboard or buttons of the code reader 1 or 1A or a communication interface (such as a USB or SD card slot). Thus, using his learned voice aV, the authorized user aN can unlock or protect operating buttons from operation by verbal commands.

[0038] Furthermore, the voice learning process is arranged to initiate the authorization of the user N by means of a predefined speech sequence, a password or a fingerprint. In particular, the authorization of the user N as an authorized user aN is to be performed at the start of the voice learning process. For this purpose, a microphone 7 or a fingerprint sensor 8 is preferably provided, by means of which the authorization of the user N can be performed.

[0039] As in the application example of the belt conveyor F shown in FIG. 1, an authorized user aN can easily perform the setting of the code reader 1 by invoking the setting function of the code reader 1 with a verbal command, even though the code reader 1 is mounted above the belt conveyor F.

[0040] A preferred embodiment of a computer-implemented method for driving the code readers 1 and 1A according to the invention will now be described with reference to FIG.

[0041] A user N or aN acoustically activates the code reader 1 or 1A, for example by transmitting to said code reader 1 or 1A an instruction stored in the evaluation unit 5 of said code reader 1 or 1A.

[0042] The code reader 1 or 1A recognises the command and activates a voice recognition process stored in the evaluation unit 5. The code reader 1 or 1A then asks the user N or aN to prove his / her authorization by reproducing a spoken sequence or a password or by scanning a fingerprint, which spoken sequence, password or fingerprint are stored in the evaluation unit 5.

[0043] If the required speech sequence is not captured and thus user N does not indicate authorization, the voice recognition process of the code reader 1 or 1A learns the captured voice V of user N as the voice V of unauthorized user N. The unauthorized user N can then activate the code reader 1 or 1A with his own voice V and display its information. However, user N cannot access high priority functions, especially safety-related functions (such as settings of the code reader 1 or 1A).

[0044] Once the speech sequence, password or fingerprint has been correctly transmitted to the code reader 1 or 1A and authorization has been recognised, the voice recognition process of the code reader 1 or 1A requests the user aN, who has been recognised as authorized, to repeat the predetermined speech sequence.

[0045] The speech recognition process recognizes and associates a voice reproducing a given speech sequence as the personal voice aV of an authorized user aN, so that the voice aV is personalized, in particular by machine learning the personalized voice aV with an artificial intelligence or re-recognizing it by comparison with stored voice patterns of the authorized user aV, so that different voices V or aV are distinguished from each other based on the learned voice patterns.

[0046] At least one predefined function of the code reader 1 or 1A is permitted to an authorized user aN associated with said personalized voice aV, which predefined function is executed when a verbal command is captured by the voice unit 6 with said personalized voice aV, in particular a measurement operation or a setting of the code reader 1 or 1A is started or ended with said personalized voice aV.

[0047] This means that the authorized user aN can start and stop certain functions of the code reader 1 or 1A by verbal commands with his / her personalized voice aV. In particular, the authorized user aN can configure the code reader 1 or 1A even if he / she does not have unhindered access to the code reader 1 or 1A, for example as depicted in Fig. 1. In particular, the permitted certain functions of the code reader 1 or 1A can also include enabling or disabling hardware elements, such as a keyboard, buttons or a communication interface (in particular a USB or SD card slot), by verbal commands, so that the authorized user aN can protect such hardware elements, for example against manipulation, by verbal commands.

[0048] Preferably, the personalized voice aV of the authorized user aN is stored as a data set which can be transmitted to another code reader 1A so that certain functions are permitted for the authorized user aN also in said other code reader 1A, so that the authorized user aN can activate or deactivate said functions with his own voice aV also in the other code reader 1A. [Explanation of symbols]

[0049] 1, 1A...Code reader 2, 2A ... Reading area of ​​the code reader 3. Lighting unit 4. Receiving unit 5...Evaluation unit 6…Sound unit 7...Microphone 8. Fingerprint sensor aN…Authorized user aV…Personalized / Authorized Voice F: Belt conveyor M…Code N...User O…Top surface P…Luggage TR: Transport direction V…Voice

Claims

1. A code reader (1, 1A) for reading an optical code, comprising: an illumination unit (3) for illuminating the reading area (2, 2A) of the code reader (1, 1A); a receiving unit (4) for detecting the code from said reading area (2, 2A), an evaluation unit (5) for determining the information of said code, and A speech unit (6) for capturing the voice (a, V) of a user (a or N) Equipped with the evaluation unit (5) is configured to perform a voice learning process in which the voice (aV or V) is learned and stored as a personal voice (aV) of an authorized user (aN), so that the voice (aV) is stored as a personalized voice (aV) of the authorized user (aN); The evaluation unit (5) is further configured to perform a voice recognition process to recognize the personalized voice (aV) as the voice of the authorized user (aN) and is further configured to perform the functions of a code reader (1, 1A) only if the personalized voice (aV) of the authorized user (aN) is recognized.

2. 2. The code reader (1, 1A) according to claim 1, wherein the evaluation unit is further configured to start the voice learning process only if authorization of the user (aN) is confirmed by a predefined speech sequence, a password or a fingerprint.

3. 3. The code reader (1, 1A) according to claim 2, wherein a microphone (7) or a fingerprint sensor (8) is provided for performing said authorization.

4. 3. The code reader (1, 1A) according to claim 2, wherein the predetermined speech sequence is stored in the evaluation unit (5) of the code reader (1, 1A) and is provided for re-recognizing or learning the voice of the authorized user (aN) by the voice recognition process.

5. 2. The code reader (1, 1A) according to claim 1, wherein the predetermined functions permitted to the authorized user (aN) include starting or stopping measurements of the code reader (1, 1A) or setting the code reader (1, 1A).

6. The code reader (1, 1A) according to claim 1, further comprising an artificial intelligence for machine learning the voice (aV) of the authorized user (aN) and for distinguishing the voice (aV) of the authorized user (aN) from the voices of other users (N), in particular unauthorized users (N).

7. 2. The code reader (1, 1A) according to claim 1, wherein the voice recognition process is configured to perform a prioritization of the recognized voices (aV) and to associate different prioritized code reader (1, 1A) functions depending on the voice priorities.

8. 2. The code reader (1, 1A) according to claim 1, wherein the learned and personalized voice (aV) can be stored in a memory device of the code reader (1, 1A) and can be transmitted to an evaluation unit (5) of another code reader (1, 1A).

9. 2. The code reader (1, 1A) according to claim 1, wherein the evaluation unit (5) is adapted to audibly or visually indicate to the authorized user (aN) whether the execution of the voice recognition process was successful or not.

10. A computer-implemented method for driving a code reader (1, 1A) equipped with a voice unit (6) for capturing an acoustic signal of the voice (V or aV) of a user (aN, N), comprising: Capturing a speech sequence of said user (aN,N); learning a voice (V) of an authorized user (aN) as a personal voice (aV), storing the voice (aV) as a personalized voice (aV), and authorizing a predetermined function of the code reader (1, 1A) for the authorized user associated with the personalized voice (aV); and Executing said predetermined function when a function invocation is captured by said speech unit (5) as a verbal command using said personalized voice (aV). A computer-implemented method comprising the steps of:

11. 11. The computer-implemented method of claim 10, further comprising obtaining a predefined speech sequence, a password or a fingerprint to verify authorization of a user (aN) to initiate voice personalization.

12. 11. The computer-implemented method of claim 10, further comprising machine learning the voices (V, aV) using artificial intelligence to distinguish between different voices (V, aV) based on learned speech patterns.

13. 11. A computer-implemented method according to claim 10, characterized in that a measurement run or a setting of the code reader (1, 1A) is started or ended with the personalized voice (aV).

14. 11. A computer-implemented method according to claim 10, further comprising storing the personalized voice (aV) of the authorized user (aN) as a data set and sending it to other code readers (1, 1A) so that the predetermined functions of the other code readers (1, 1A) are granted to the authorized user (aN).

15. A computer-implemented method according to any of claims 10 to 14, comprising distinguishing between recognised voices (V, aV), assigning different priorities to the recognised voices (V, aV) and granting the prioritized voices (aV) access to corresponding predefined functions of the code reader (1, 1A).

Images