EP3533054A1

EP3533054A1 - Task management method

Info

Publication number: EP3533054A1
Application number: EP17783466.0A
Authority: EP
Inventors: Denis DECUBBER; Claude DEDRY; Raphaël BENEDET; Stéphane Focant; Jean-Sébastier DECUBBER; Manuel BASILAVECCHIA
Original assignee: Salamander U
Current assignee: Salamander U
Priority date: 2016-10-25
Filing date: 2017-10-10
Publication date: 2019-09-04
Also published as: FR3057974B1; EP3533010A1; BE1024252B1; WO2018077608A1; BE1024252A1; FR3057974A1; WO2018077900A1; US20190244155A1; US20190271963A1; CA3039571A1; CA3040210A1

Abstract

The present invention relates to a method for managing the tasks of a given procedure to be carried out by at least one operator in a regulatory environment, whereby: the operator receives voice commands from a computer system relating to the execution of the tasks of the procedure; the operator reports the execution of the tasks orally to the computer system; and the execution of the tasks is controlled by means of the computer system.

Description

Task management method

The invention relates to the field of industrial production in which precise, regulated and controlled procedures must be followed by operators. Although industrial production is increasingly automated, some types of production can only be implemented by operators. This is the case, for example, of textile productions or certain agro-food products.

This is also the case for biological or pharmaceutical productions, such as vaccines or cell or gene therapies, which must be carried out in a sterile environment, according to very strict standards and must be permanently monitored for quality. The procedures, or recipes, established for these productions must be followed to the letter by the operators, and a certain number of parameters must be measured and recorded during the production cycle.

Usually, for these productions in sterile clean room, a procedure, enumerating the tasks to be carried out and the framework to respect for the parameters related to these tasks, is written by the production managers. It is then printed on paper, decontaminated by irradiation, transmitted to a pair of operators who take with them the procedure printed in a clean room, where they must wear all the protective equipment - overalls, gloves, mask, glasses, ... One of the operators is in charge of the manual operations, the second operator is in charge in particular to read the procedure to his colleague and to note the parameters measured by this one. In fact, the operator who performs the manual operations who is provided with sterile gloves or has the arms introduced into a glove box or a laminar flow can not, at the same time, handle a form and a pencil. This operator may also need glasses to read written documents, while he does not need them to perform his task. If he was alone, he would have to remove and put back his glasses and / or some of his equipment to read the procedure.

At the end of the production cycle, the notes taken by the operator are sent to the personnel in charge of verifying and validating the quality of the production before being able to authorize the release of the product batch and its placing on the market. . It is also possible that instead of being printed, the procedure is available for reading on a computer screen. In this case, the second operator reads the instructions to his colleague from the computer screen and saves the measured parameters in the computer.

Whether the procedure is read on paper or on a computer screen, the second operator is essential, both to free the hands of the operator who performs the operations that to double-check the operations performed by his colleague. These production characteristics are not only found in sterile clean rooms. Some of these characteristics are also applied in the agri-food sector, where the cold chain must be scrupulously respected, or even in the microelectronics sector, where production is carried out in dust-free clean rooms.

This mode of production has a number of disadvantages. First of all, the use of a printed procedure requires a preliminary step of decontaminating the paper when it is introduced into the sterile or dust-free loca l. It is then necessary to retranscribe the measured parameters on the documents. Second, having two operators perform the production instead of one has a significant impact on the cost of production. This cost is particularly prohibitive for small productions, as for example for cell or gene therapies, where the batch produced may be different for each patient (in the case of autologous productions).

The production cycle must also be completed until it has been submitted to quality control. A batch can therefore be rejected after being entirely produced, while the problem causing its rejection occurred at the beginning of the production stages. Unnecessary costs were then implemented, both in terms of the time spent by the operators and the level of material resources that could have been saved.

Finally, the margin of error due to the subjectivity of the operators in their decision making in the course of their tasks is not negligible. This induces a variability in the quality of the batches produced, in particular between batches produced by different operators.

It has therefore been deemed necessary by the Applicant to propose a production method and a tool for implementing this method to eliminate the above problems.

The present invention proposes for this purpose and first of all a task management method of a given recipe to be carried out by at least one operator in a regulatory environment, a method according to which the operator receives from a computer system orders the performance of the recipe tasks,

- the operator performs the tasks,

the operator orally reports to the computer system the execution of the tasks and the execution of the tasks is controlled via the computer system, the control of the execution of the tasks including the comparison of the information reported by the operator with an advance information previously entered in the recipe, said advance information being one of the elements of the group comprising a value, a range of values, a term and an expression and the control integrating the result of the task check into the selection of a new order to be issued.

Thanks to the invention, a single operator can carry out the tasks of a procedure that he must follow, with a quality control and a decision support for each task, in order to reduce on the one hand the costs of production while improving quality.

Advantageously, for the execution of a task, a dialogue can be established between the operator and the computer system.

The recipe can be previously entered on the computer system.

The computer system can also cooperate with other computer systems for controlling the execution of tasks.

The execution of the tasks can be memorized via the computer system. The computer system can then generate a report relating to the execution of the tasks or participate in the generation of this report.

By regulatory environment, one must understand an environment subject to a set of rules. These rules may come from specific legislation and related to compliance with standards, health, safety or quality. They may also come from internal regulations of a company or organization, relating to the specifications to be complied with or the constraints defined by the company or organization. The present invention also proposes, as an intermediate product, a task management algorithm of a given recipe to be produced by at least one operator in a regulatory environment for the implementation of the method of the invention, arranged to emit voice commands to perform recipe tasks for the operator, receive an oral report of the execution of tasks and

- participate in the control of the execution of tasks.

Advantageously, the algorithm is arranged to integrate the result of the task control into the selection of a new order to be issued.

The algorithm may also include a module for writing the recipe.

In order to improve the quality of the interaction between the computer system and the operator, the algorithm comprises a speech recognition module associated with a specific grammar to receive the oral report.

The algorithm can optionally be arranged to integrate external data to control the execution of tasks. The invention will be better understood with the aid of the following description of several implementations of the invention, with reference to the appended drawing in which: FIG. 1 schematically illustrates the method of the invention;

FIG. 2 illustrates the cooperation between the operator and the algorithm of the method of FIG.

FIG. 3 illustrates the detail of certain steps of the method of FIG.

With reference to FIG. 1, according to the task management method of a given recipe, to be carried out by an operator 2, and comprising at least one task 1, an operator 2 interacts with a computer system 3 according to the following steps:

A: the order of execution of the task is communicated vocally to the operator 2 by the computer system 3,

B: the operator executes the task,

C: the operator orally reports the execution of the task to the computer system and D: the execution of the task is controlled by the computer system 3.

With reference to FIG. 2, the task management algorithm 10, which makes it possible to implement the method of the invention, is implemented on the computer system 3, which comprises a data storage unit 11 and in which the task 1 of recipe 4 to execute. The algorithm 10 comprises a voice synthesis module 5, a voice recognition module 6 and a control module 7. The operator 2 is meanwhile equipped with an audio headset 8 and a microphone 9 cooperating with the system 3. Concretely, the recipe 4 which has been entered in the computer system 3 includes a certain number of tasks to be performed by the operator 2, manually, with or without the aid of tools. Each task 1 has a number of features that must be monitored, measured, observed or applied by the operator.

During step A, using the speech synthesis module 5, the task 1, initially stored in the form of digital data is transcribed into a voice message of execution order, which is sent by the audio system, here a headphones 8, to the operator 2. The headphones 8 can advantageously communicate wirelessly with the computer system 3.

During step B, the operator 2 will execute the task 1. In the case where particular characteristics must be recorded by the operator 2, the latter may be invited by another audio message, to provide these features verbally, and this can be considered a separate task.

Thus, during step C, the operator 2 will report the execution of the task 1 by stating a message in his microphone 9. His oral message will be analyzed by the voice recognition module 6 and retranscribed in digital data. .

Here again, the voice recognition module is perfected and includes a specific grammar adapted to the recipe; for each message given by the operator, a particular register or a series of particular response values according to the recipe is available to the computer system for interpreting the message. For example, if the operator must enter a number, the voice recognition module 6 can only transcribe the operator's message in one digit. This feature is particularly interesting when the operator is working in a noisy environment and allows much more reliable communication between the operator and the computer system. To further improve the reliability, the computer system 3 invites the operator, by another voice message, to confirm his good interpretation of the message.

The message of the operator 2, relating to the execution of the task, can be varied in nature. The operator can simply inform the status of the task, for example that he has finished, give the numerical value of a measurement he has made, or fill in an observation he has made. It may also be expected that certain messages from the operator have a particular function. The operator could for example ask the computer system to repeat the task, or to pause.

During step D, the control module 7 of the algorithm analyzes the content of the message or oral report of the operator 2 and decides on the continuation of the process. The analysis is done in particular by comparing this oral report with an advance information previously entered in the recipe 4. The anticipated information may be a value, a range of values, a term or an expression. The computer system has autonomous decision-making capability resulting from the parameters of the recipe.

For example, if the operator 2 indicates that he has finished a task, the control module 7 can instruct the computer system 3 to communicate the next task. If the operator 2 has entered a numerical value, the control module 7 can possibly carry out a certain number of calculations integrating this numerical value, compare it with its anticipated value and decide on the next instruction to be given to the operator, for example the cessation of operations if the deviation from the value with the anticipated value is too great or the completion of the next task if the value is in conformity. The criteria of conformity or nonconformity are defined during the drafting of recipe 4.

Finally, the operator can also provide a non-critical characteristic to the production process, for example a simple observation, the expiry date of an ingredient or the reference of an equipment. In all cases, the messages of the operator 2 relating to the execution of the tasks are recorded by the computer system 3 in a data storage unit 11 and may be used later, for example for writing a report of performance of the recipe or a quality report to regulatory authorities or a certificate of analysis for customers. Optionally, a report relating to the executed tasks is generated directly by the computer system 3.

The speech synthesis module 5 refers to a sound synthesis computer technique that makes it possible to create artificial speech from any text. Such a module comprises elements of linguistic processing, in particular for transforming the orthographic text into an unambiguously pronounced phonetic version, and signal processing elements for transforming this phonetic version into digitized sounds that can be listened to on a loudspeaker, for example here integrated 8. The voice recognition module 6 contains the inverse elements for transforming a sound recorded by a microphone into digital text. Speech synthesis and speech recognition are technologies for building voice interfaces and are used in particular for the vocalization of computer screens for blind people or at the level of telephone voice servers.

It is also conceivable to couple these modules with a translation module, thus enabling the operator to choose the language in which he wishes to communicate with the computer system 3. This can be interesting when several production sites located in different countries must implement the same process.

A simplified example of the method of the invention, applied to the implementation of a cell seeding procedure, is illustrated in FIG.

A recipe 4 of cell seeding, to be carried out in a sterile clean room, and containing several steps, has been entered in the computer system 3. An operator 2, equipped according to the standards of the room where he will perform the tasks, gathered the material necessary for the execution of the recipe, possibly according to a first recipe, not described here. He is also equipped with a headset 8 and a microphone 9. When it is ready, it starts the execution of the recipe, for example by pronouncing "ready".

The following dialog is installed between the computer system (SI) and the operator (in italics, the oral messages):

-SI: "Step 1, what is your name"

-Operator: "Mr. X" (The name of the operator can be used to check if he has all the valid authorizations necessary to the execution of this task, in real time if the operators' authorization database cooperates with the computer system enabling the implementation of the method or later in the opposite case.)

-SI: "Step 2, enter the laminar flow code used for the operations"

-Operator: "1256" (The equipment number can thus be associated with its maintenance profile, in real time if the equipment maintenance database cooperates with the computer system allowing the implementation of the process or later in the future. the opposite case.)

-SI: "enter the code of the temperature probe used for the operations" -Operator: "1724" -SI: "Step 3: prepare a vial of 100 milliliters of human serum. With the probe measure the temperature of the bottle and enter the value of the temperature »

-Operator: "37"

-SI: "Step 4, transfer the T175 flanges under the laminar flow. Check 1: How many flanges did you transfer? »- Operator:« 2 »

Here, the number of flange can affect the following instructions, for example on the setting parameters of the centrifuge.

-SI: "Using a 50-ml pipette, transfer the cell suspension from each T175 flask to a 500-ml tube. Say finished when you're done "- operator:" finished "

-SI: «Step 5: Set the centrifuge according to the following parameters: acceleration 1600 g, temperature 20% time 10 min. Put the tubes containing the cells in the centrifuge cup and start the centrifugation. Say finished when the centrifugation is over. "

-operator: "finished" -SI: "Step 6: With a micropipette of 200 microliters, transfer 30 microliters of suspension into a 1.5 milliliter tube containing cells and 30 microliters of suspension into an empty tube. Add in each of the two tubes 30 microliters of PBS and 60 microliters of "Trypan blue". Mix well and introduce 20 microliters of each dilution into a chamber of the Neubauer plate. Start the measurement. How many cells were counted "- Operator:" 1732 " The control module will correct the value of 1732 using the dilution coefficients used, and possibly the parameters related to the particular equipment used, then compare the result obtained with the expected values for this measurement. If for example the calculated value is lower than the values of the expected range, and in this case the process has to be stopped, the following message can be issued:

-SI: "Control 2: the number of cells is insufficient. Step 7: Remove the cells in the biological waste bin. Say finished when you're done. "

-operator: "finished"

If the number of cells had been sufficient, the seeding instructions of Step 8 could have been given.

-SI: "Step 9. -It is the end of operations in the laminar flow, please clean and tidy up your work plan. Take the environmental samples corresponding to the end of the operations. Say finished when you're done and leave the room. "

-Operator: "finished". In parallel with this dialogue between the operator 2 and the computer system 3, all the information received from the operator has been recorded in the data storage unit 11. This information may be used by the persons in charge of establishing the report of the operations, to validate a lot, or to trace all the elements which intervened in the production of a product, for example by the persons of the quality service or the people in charge of the production who will want to seek to understand why the Seeding of the cells failed. This information can also be used to generate statistics.

It is not excluded that in some cases the recipe provides for the use of an external controller, for example the production manager or the team leader. In this case, a function can be provided on the computer system so that the operator in the sterile room can communicate orally with the external controller positioned outside.

Advantageously, the computer system 3 may also include a module for assisting with the writing of the recipe 4. This module may for example provide predefined steps in which some parameters may be modified. This configuration, which limits to a certain extent the range of grammar used by the editor of the recipe, makes it possible in particular to limit the errors of interpretation of the tasks. It can also allow the editor of the recipe to remain compliant with the standards or rules in force by preventing it from leaving the regulatory framework and by pre-defining a number of control steps. It is obvious that the method described above is not limited to sterile room biological operations, but can be applied to many environments. An example is the nuclear sector, where strict procedures must be implemented to limit the exposure of operators to radioactive radiation. The analysis of the quantities of radiation received by the operator can for example determine the number of tasks that he will have to perform, while taking into account the time he needs to perform the essential tasks of the end of the procedure. to say the decontamination.

The method of the invention makes it possible to save time thanks to the impartial and real-time decision-making by the computer system on the steps of the recipe to be implemented according to the information given by the operator, without needs to enter information on a computer, or write it on a paper, which should be subsequently decontaminated, while a simple headphone 8 and a microphone 9 can easily be inserted into his equipment .

Claims

claims

A method for managing tasks of a given recipe (4) to be performed by at least one operator (2) in a regulatory environment, a method according to which

the operator receives from the computer system (3) voice commands for performing the tasks (1) of the recipe (4),

the operator (2) performs the tasks (1),

the operator (2) reports to the computer system (3) the execution of the tasks (1) and

the execution of the tasks (1) is controlled via the computer system ^), the control of the execution of the tasks (1) comprising the comparison of the information reported by the operator (2) with an advance information , previously entered in the recipe (4), said anticipated information being one of the elements of the group comprising a value, a range of values, a term and an expression and the control integrating the result of the task control (1) into the selection of a new order to be issued.

2. Method according to claim 1 in which a dialogue is established between the operator (2) and the computer system (3).

3. Method according to one of claims 1 and 2, wherein the recipe (4) is previously informed on the computer system (3).

4. Method according to one of claims 1 to 3, wherein the computer system (3) cooperates with other computer systems for controlling the execution of tasks (1).

5. Method according to one of claims 1 to 4, wherein the computer system (3) generates a report relating to the execution of tasks (1).

6. Method according to one of claims 1 to 5, wherein the execution of the tasks (1) is stored via the computer system (3).

7. Algorithm (10) for managing tasks (1) of a given recipe (4) to be performed by at least one operator (2) in a regulatory environment for implementing the method of claims 1 to 6, arranged to issuing voice commands for performing the tasks (1) of the recipe (4) for the operator (2),

receive an oral report of the execution of tasks (1) and

participate in the control of the execution of tasks (1).

8. Algorithm (10) according to claim 7, arranged to integrate the result of the task control (1) in the selection of a new order to be issued.

9. Algorithm (10) according to one of claims 7 and 8, comprising a module for assisting the writing of the recipe (4).

10. Algorithm (10) according to one of claims 6 to 9, comprising a voice recognition module (6) associated with a specific grammar to receive the oral report.

11. Algorithm (10) according to one of claims 6 to 10, arranged to integrate external data when controlling the execution of tasks (1).

12. Algorithm (10) according to one of claims 7 to 11, wherein the algorithm (10) analyzes the content of the oral report of the operator (2) by comparison with an advance information, previously filled in the recipe ( 4), said anticipated information being one of the elements of the group comprising a value, a range of values, a term and an expression.

13. Algorithm (10) according to one of claims 7 to 12, arranged to participate in the drafting of a report on the execution of tasks.