Conference solution pushing method based on smart factory and medium

Abstract

The invention relates to a smart factory-based conference solution pushing method and a medium, and relates to the technical field of online conferences. Based on the audio information and / or text information of the online conference, obtaining first conference participation information and first fault information in real time; the first conference participation information comprises conference participants and conference content; the first fault information comprises a fault object, fault data and a fault solution, and the fault data comprises a fault type and a fault position. Taking the first participation information and the first fault information as input of a trained fault processing result prediction network, and obtaining a predicted fault processing result as a first predicted fault processing result; wherein the fault processing result comprises fault processing duration and fault processing cost. And displaying the first predicted fault processing result. Compared with the prior art, the method can assist participants in discussion and accelerate the problem solving progress, so that the problem solving working efficiency is improved, and the online conference progress is promoted.

Description

Technical Field

[0001] The present invention relates to the field of online conference technology, and in particular to a method and medium for pushing conference solutions based on a smart factory. Background Art

[0002] When a problem occurs in a factory, in order to improve communication efficiency, a separate online meeting is generally established to communicate and discuss the current problem in order to quickly form a solution. The online meeting is usually initiated by the person who discovered the problem or his supervisor, and maintenance engineers are organized to participate in the problem communication and discussion. Due to the limitations of personal work experience, maintenance engineers participating in the discussion may not be able to quickly propose solutions, which reduces the efficiency of problem solving and delays factory production. Summary of the invention

[0003] The technical problem to be solved by this application is to provide a method and medium for pushing conference solutions based on a smart factory, which has the characteristics of improving the efficiency of problem solving and promoting the progress of online meetings.

[0004] In a first aspect, an embodiment provides a method for pushing a conference solution based on a smart factory, including: Based on the audio information and / or text information of the online meeting, first conference participant information and first fault information are obtained in real time; the first conference participant information includes conference participants and conference content; the first fault information includes a fault object, fault data and a fault solution, and the fault data includes a fault type and a fault location; The first conference attendance information and the first fault information are used as inputs of a trained fault handling result prediction network, and a predicted fault handling result is obtained as a first predicted fault handling result; wherein the fault handling result includes a fault handling time and a fault handling cost; The first predicted fault processing result is displayed.

[0005] In one embodiment, after displaying the first predicted fault processing result, the method further includes: Solution 1: Collect satisfaction evaluation information on the first predicted fault handling result, and calculate the satisfaction evaluation index as the first satisfaction evaluation index; if the first satisfaction evaluation index is less than the preset first evaluation index threshold, obtain at least one fault handling result based on the database as the second predicted fault handling result, and display the second predicted fault handling result and the corresponding first meeting information and first fault information; and / or, Solution 2: Calculate the duration from the start of display of the first predicted fault handling result to the current time in real time. If the duration reaches a preset first duration threshold, obtain at least one fault handling result based on the database as the second predicted fault handling result, and display the second predicted fault handling result and the corresponding first meeting information and first fault information. The database includes a plurality of fault handling information, each of which includes first meeting participation information, first fault information, and a fault handling result; the method of obtaining at least one fault handling result based on the database as the second predicted fault handling result includes: Based on the fault object and fault data, the corresponding fault handling result in the database is searched. If there are multiple fault handling results, the fault handling time less than the preset second time threshold is used as the first constraint condition, and the fault handling results that meet the first constraint condition are sorted from low to high according to the fault handling cost, and the previously set number of fault handling results are obtained as the second predicted fault handling result; or, the fault handling cost less than the preset first cost threshold is used as the second constraint condition, and the fault handling results that meet the second constraint condition are sorted from low to high according to the fault handling time, and the previously set number of fault handling results are obtained as the second predicted fault handling result.

[0006] In one embodiment, after displaying the first predicted fault handling result, the method includes the case where the first solution is used, if the first satisfaction evaluation index is less than a preset first evaluation index threshold, obtaining at least one fault handling result based on a database as a second predicted fault handling result, including: If the first satisfaction evaluation index does not reach the preset first evaluation index threshold, the accuracy of the fault data is determined in response to the acquired monitoring data of the fault object. If the accuracy reaches the preset accuracy threshold, at least one fault processing result is obtained based on the database as the second predicted fault processing result.

[0007] In one embodiment, after displaying the second predicted fault processing result, the method further includes: Collect satisfaction evaluation information on the second predicted fault handling result, and calculate the satisfaction evaluation index as the second satisfaction evaluation index; if the second satisfaction evaluation index is less than the preset second evaluation index threshold, obtain the fault handling result ranked first in the second predicted fault handling result, and obtain the corresponding first participant information, filter out personnel who are currently on duty but are not participants in the current meeting from the first participant information, and initiate a meeting push to the smart terminals where the filtered personnel are located.

[0008] In one embodiment, updating the first fault prediction result includes: In response to the updated first conference participant information and / or the first fault information, based on the trained fault processing result prediction network, updating the first predicted fault processing result; The updated first predicted fault processing result is displayed, and the updated display time is used as the start time of displaying the first predicted fault processing result.

[0009] In one embodiment, an improvement value is calculated based on the updated first predicted fault processing result, and if the improvement value is greater than a preset value threshold, a fault solution corresponding to the updated first predicted fault processing result is used as a work result; The improvement value calculated based on the updated first predicted fault processing result includes a duration improvement value and / or a cost improvement value.

[0010] In one embodiment, the calculation of the improvement value based on the updated first predicted fault processing result includes: K1=(A1-A2) / A1, B2≤B0, and / or, K2=(B1-B2) / B1, A2≤A0, Among them, K1 represents the cost improvement value, K2 represents the time improvement value, A1 represents the fault handling cost before improvement, A2 represents the fault handling cost after improvement, A0 represents the second cost threshold, B1 represents the fault handling time before improvement, B2 represents the fault handling time after improvement, and B0 represents the third time threshold.

[0011] In one embodiment, the method further includes setting a first floating window and a second floating window; In response to the acquired first predicted fault processing result, displaying the first predicted fault processing result in a first floating window; In response to the acquired second predicted fault processing result, the second predicted fault processing result and the corresponding first conference participant information and first fault information are displayed in a second floating window.

[0012] In a second aspect, an embodiment provides a computer-readable storage medium, in which a program is stored. The program can be loaded by a processor and execute the conference solution pushing method described in any one of the above embodiments.

[0013] The beneficial effects of the present invention are: Since it is based on a trained fault handling result prediction network, the first participant information and the first fault information obtained in real time through the audio information and / or text information of the online meeting are used as input to obtain and display the predicted fault handling results, which can assist the discussion of the participants and speed up the problem solving process, thereby improving the work efficiency of problem solving and promoting the progress of the online meeting.

[0014] When the first predicted fault handling result is not satisfactory, and / or when no new solution is extracted within a preset time from the first predicted fault handling result, the second predicted fault handling result is initiated; on the basis of reducing the communication cost of fault meetings and improving communication efficiency, a certain amount of time is provided for personnel to accumulate fault handling experience, so as to generate new solutions and fault handling results, enrich the database, and provide more reserve solutions and experience for subsequent fault resolution.

[0015] The improvement value is calculated based on the updated first predicted fault handling result. If the improvement value is greater than the preset value threshold, the fault solution corresponding to the updated first predicted fault handling result is used as the work result. Based on the work result, the participants can be encouraged to further propose solutions to technical problems and improve technical solutions, speed up the progress of problem solving, thereby improving the work efficiency of problem solving and promoting the progress of online meetings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of a conference solution push method according to an embodiment of the present application; Figure 2 This is a flowchart of a conference solution push method according to another embodiment of the present application; Figure 3 is a flowchart of a method for obtaining at least one fault processing result based on a database as a second predicted fault processing result according to an embodiment of the present application; Figure 4 This application Figure 2 A method flow chart of an embodiment of step S60 in FIG. DETAILED DESCRIPTION

[0017] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present application better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present application are not shown or described in the specification, this is to avoid the core part of the present application being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0018] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate manner to form various implementations. At the same time, the steps or actions in the method description can also be interchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for the purpose of clearly describing a certain embodiment and are not meant to be a required sequence, unless otherwise specified that a certain sequence must be followed.

[0019] The serial numbers assigned to the components herein, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning. The "connection" and "coupling" mentioned in this application, unless otherwise specified, include direct and indirect connections (couplings).

[0020] To facilitate the description of the inventive concept of this application, the online conference technology is briefly described below.

[0021] In the current online meeting discussions on technical issues, the background management system will split the content of the conversation archive into departments, problem descriptions, solutions, initiators and reviewers, etc., save the content to the database, and support the export of reviewed content.

[0022] However, the applicant found in the research that during the discussion process of solving technical problems in online meetings, due to insufficient experience in solving technical problems, the discussion would often get stuck on a certain technical detail and be unable to continue, or deviate from the meeting topic, resulting in low meeting discussion efficiency.

[0023] In view of this, an embodiment of the present application provides a conference solution push method and medium based on a smart factory. Based on a trained fault handling result prediction network, the first participant information and the first fault information obtained in real time through the audio information and / or text information of the online meeting are used as input to obtain and display the predicted fault handling results to assist the discussion of the participants, speed up the problem solving process, thereby improving the work efficiency of problem solving and promoting the progress of online meetings.

[0024] In order to clearly illustrate the method for pushing conference solutions based on smart factories in the embodiment of the present application, the training method of the fault handling result prediction network is first described below.

[0025] Since the current backend management system will split the content of the session archive into departments, problem descriptions, solutions, initiators, and reviewers, etc. Based on these archived information, a large amount of historical fault handling solutions and meeting information can be obtained. Screen and organize these data to obtain the first meeting information, the first fault information, and the fault handling results, where the first meeting information includes meeting participants and meeting content; the first fault information includes fault objects, fault data, and fault solutions, and the fault data includes fault type and fault location; the fault handling results include fault handling time and fault handling cost. Construct a training data set to obtain an N×M input vector for training, where N represents the row in the input vector matrix, each row is a one-dimensional vector containing M data, and the data of each one-dimensional vector includes meeting participants, meeting content, fault objects, fault type, fault location, and fault solution.

[0026] Construct a preliminary network framework for the fault handling result prediction network, take the input vector as input, perform feature extraction, and combine the constructed loss function to train the preliminary network framework for the fault handling result prediction network to obtain the final fault handling result prediction network.

[0027] The applicant discovered during the research that in the current technology, the neural network used for fault prediction only includes physical parameter information related to the fault in the training data. Even when predicting the fault handling results, only physical and technical factors are considered.

[0028] However, the processing personnel often have a great influence on the fault handling results. For example, for the same processing plan, different processing personnel will have different ways of handling details, and it is often difficult to record these subtle processing details in the processing plan, which makes the fault handling results obtained different even for the same processing plan. Therefore, the training data of the fault handling result prediction network based on the embodiment of the present application includes the meeting participants.

[0029] The meeting content may include project content information. The fault object may be equipment or connectors, such as a pipeline. The fault type may be a manifestation of a fault such as leakage or deformation. The fault location includes the specific location of the fault on the fault object, such as a connection of a pipeline.

[0030] Based on the fault handling result prediction network obtained through the above training, an embodiment of the present application provides a conference solution push method based on a smart factory, please refer to Figure 1 ,include: Step S10, based on the audio information and / or text information of the online meeting, first conference participant information and first fault information are obtained in real time.

[0031] The first meeting information includes meeting participants and meeting content. Meeting participants here include all people who participate in the meeting discussion. The first fault information includes fault object, fault data and fault solution. The fault data includes fault type and fault location.

[0032] In step S10, the first conference participant information and the first fault information can be extracted based on the audio information of the online conference only, or can be extracted based on the input text information only. In one embodiment, the first conference participant information and the first fault information are obtained based on the audio information and text information of the online conference.

[0033] In one embodiment, the extracted first conference participant information is displayed and confirmed by the client to ensure the integrity of the extracted first conference participant information.

[0034] In one embodiment, the extracted first fault information is displayed and confirmed by the client to ensure the integrity of the extracted first fault information.

[0035] Step S20: taking the first conference participant information and the first fault information as inputs of the trained fault handling result prediction network, and obtaining a predicted fault handling result as a first predicted fault handling result, wherein the fault handling result includes the fault handling time and the fault handling cost.

[0036] Step S30, displaying the first predicted fault processing result.

[0037] In one embodiment, a first floating window is provided, and in response to the obtained first predicted fault processing result, the first predicted fault processing result is displayed in the first floating window. The setting of the first floating window can facilitate the participants to move the position of the floating window and set the size of the floating window, so as to flexibly set the current meeting page based on the convenience of meeting discussion.

[0038] A conference solution push method based on any one of the above embodiments, During the research, the applicant found that during the meeting, the participants may change, the meeting content may have supplementary descriptions, and the description of the first fault information may also change, such as adding the fault location, or describing the fault location more accurately, supplementing the description of the fault solution, etc.

[0039] In view of this, in one embodiment, it is determined whether there is a change in the first conference participant information. If so, in response to the changed first conference participant information, based on a trained fault handling result prediction network, the first predicted fault handling result is updated and displayed.

[0040] In one embodiment, it is determined whether there is a change in the first fault information. If so, in response to the changed first fault information, based on the trained fault processing result prediction network, the first predicted fault processing result is updated and displayed.

[0041] In some embodiments, the updated first predicted fault processing result may be displayed below or above the first predicted fault processing result before the update, or may directly replace the first predicted fault processing result before the update for display.

[0042] In one embodiment, the changed first conference participant information and / or first fault information is displayed and confirmed by the client to ensure the integrity of the extracted updated first conference participant information and / or first fault information. The first predicted fault processing result is updated based on the confirmed first conference participant information and / or first fault information.

[0043] In one embodiment, an improvement value is calculated based on the updated first predicted fault processing result. If the improvement value is greater than a preset value threshold, the fault solution corresponding to the updated first predicted fault processing result is used as the work result.

[0044] Based on the results of this work, participants can be encouraged to take the initiative to further propose solutions to technical problems and improve technical solutions, speed up the problem-solving process, thereby improving the efficiency of problem-solving and promoting the progress of online meetings.

[0045] In one embodiment, the technical solution improvers who achieve the work results are recorded synchronously.

[0046] In some embodiments, the improvement value is calculated based on the updated first predicted fault processing result, including the duration improvement value and / or the cost improvement value. If only the duration improvement value or the cost improvement value meets the preset value threshold, the corresponding fault solution will be taken as the work result. Alternatively, both the duration improvement value and the cost improvement value need to meet the preset value threshold before the corresponding fault solution will be taken as the work result.

[0047] In one embodiment, in calculating the improvement value based on the updated first predicted fault processing result, the method for calculating the duration improvement value can be expressed as: K1=(A1-A2) / A1, B2≤B0, Among them, K1 represents the cost improvement value, A1 represents the fault handling cost before improvement, A2 represents the fault handling cost after improvement, B2 represents the fault handling time after improvement, and B0 represents the third time threshold. Let B2≤B0 be the constraint condition for solving K1, and K1 is obtained when B2≤B0 is satisfied.

[0048] In some embodiments, A1 may be the fault handling cost in the first predicted fault handling result obtained first, or may be the fault handling cost of the first predicted fault handling result before the current first predicted fault handling result. Those skilled in the art may set the cost value threshold that the cost improvement value needs to meet based on actual needs.

[0049] In one embodiment, in calculating the improvement value based on the updated first predicted fault processing result, the method for calculating the duration improvement value can be expressed as: K2=(B1-B2) / B1, A2≤A0, Among them, K2 represents the duration improvement value, A2 represents the improved fault handling cost, A0 represents the second cost threshold, B1 represents the fault handling duration before improvement, and B2 represents the improved fault handling duration. Let A2≤A0 be the constraint condition for solving K2, and K2 is obtained when A2≤A0 is satisfied.

[0050] In some embodiments, B1 may be the fault processing time in the first predicted fault processing result obtained first, or may be the fault processing time in the first predicted fault processing result before the current first predicted fault processing result. Those skilled in the art may set the time value threshold that the time improvement value needs to meet based on actual needs.

[0051] In one embodiment, when there are multiple work results, the work results are sorted. In one embodiment, the work results are sorted from large to small according to the improvement value. If the improvement value includes the time improvement value and the cost improvement value, they are sorted separately.

[0052] The applicant found in the study that if the meeting participants cannot propose further improvement plans and are not satisfied with the current troubleshooting results, the current meeting will be difficult to move forward, which will affect the work efficiency and meeting progress in solving the current technical problems.

[0053] In view of this, in one embodiment, please refer to Figure 2 , after step S30, further comprising: Step S40, obtaining a second predicted fault processing result.

[0054] In one embodiment, the method for obtaining the second predicted fault processing result may include: Collect satisfaction evaluation information on the first predicted fault handling result. In one embodiment, satisfaction evaluation information on the first predicted fault handling result can be collected based on the audio information and / or text information of the online meeting, and the satisfaction evaluation index can be calculated as the first satisfaction evaluation index. The first satisfaction evaluation index can be calculated based on the satisfaction level of each meeting participant. If the first satisfaction evaluation index is less than the preset first evaluation index threshold, it means that the current first predicted fault handling result is not satisfactory. Then, at least one fault handling result is obtained based on the database as the second predicted fault handling result.

[0055] In one embodiment, if the first satisfaction evaluation index does not reach the preset first evaluation index threshold, the accuracy of the fault data is determined in response to the acquired monitoring data of the fault object, and if the accuracy reaches the preset accuracy threshold, at least one fault processing result is obtained based on the database as the second predicted fault processing result. In this way, misunderstandings and deviations are reduced, ensuring that meeting participants have a clear understanding of the fault processing goals, task allocation and expected results, reducing the time cost of communication and improving fault processing efficiency.

[0056] Those skilled in the art can understand that in the current online conference technical problem solving discussion, the backend management system will split the content of the session archive into the department, problem description, solution, initiator and reviewer, etc., and save the content to the database. Based on the saved database, it includes fault handling information, each fault handling information includes the first meeting information, the first fault information and the fault handling result. Then, at least one fault handling result is obtained based on the database as the second predicted fault handling result, please refer to Figure 3 , which may include: Step S100: searching for corresponding fault processing results in a database based on the fault object and fault data.

[0057] Step S200, determine whether there are multiple fault processing results, if yes, proceed to step S300, if not, proceed to step S400.

[0058] Step S300: obtaining a second predicted fault processing result based on the first constraint condition, or obtaining a second predicted fault processing result based on the second constraint condition.

[0059] Among them, obtaining the second predicted fault handling result based on the first constraint condition includes: taking the fault handling time being less than a preset second time threshold as the first constraint condition, sorting the fault handling results that meet the first constraint condition from low to high according to the fault handling cost, and obtaining the previously set number of fault handling results as the second predicted fault handling result.

[0060] In one embodiment, the second duration threshold may be equal to the third duration threshold.

[0061] Obtaining a second predicted fault handling result based on a second constraint condition, including: taking a fault handling cost less than a preset first cost threshold as a second constraint condition, sorting the fault handling results that satisfy the second constraint condition from low to high according to the fault handling time, and obtaining a previously set number of fault handling results as the second predicted fault handling result.

[0062] In one embodiment, the first cost threshold may be equal to the second cost threshold.

[0063] The above-mentioned set number can be set based on actual needs. In one embodiment, 3 can be used as the set number, that is, the fault processing results ranked in the top 3 are obtained as the second predicted fault processing results. It can be understood by those skilled in the art that although the set number is 3, if the total number of fault processing results that meet the first constraint condition or the second constraint condition is less than 3, the actual fault processing result that meets the first constraint condition or the second constraint condition shall prevail.

[0064] Step S400: taking only one fault processing result obtained as the second predicted fault processing result.

[0065] In one embodiment, the method for obtaining the second predicted fault handling result may include: calculating in real time the duration from the start of display of the first predicted fault handling result to the current time, if the duration reaches a preset first duration threshold, it means that the meeting participants may not have been able to propose further improvement plans for a long time, and the current meeting progress is slow, then obtaining at least one fault handling result based on the database as the second predicted fault handling result. The method for obtaining at least one fault handling result based on the database as the second predicted fault handling result can refer to the process of step S100 to step S400.

[0066] In one embodiment, if the first predicted fault processing result is updated, the updated display time is used as the start display time of the first predicted fault processing result.

[0067] Based on the second predicted fault handling result obtained in any of the above embodiments, previous fault handling solutions and fault handling results can be used as a reference for meeting participants to further promote solutions to current technical problems, thereby improving the work efficiency of solving current technical problems and promoting the progress of the meeting.

[0068] Step S50, displaying the second predicted fault processing result and the corresponding first conference participant information and first fault information.

[0069] In one embodiment, a second floating window is set, and in response to the obtained second predicted fault processing result, the second predicted fault processing result and the corresponding first conference participant information and first fault information are displayed in the second floating window. The setting of the second floating window can facilitate the participants to move the position of the floating window and set the size of the floating window, so as to flexibly set the current meeting page based on the convenience of meeting discussion.

[0070] In addition, the first floating window and the second floating window are separately arranged, and the first predicted fault processing result and the second predicted fault processing result are displayed separately, so as to facilitate comparison, improve work efficiency, and promote meeting progress.

[0071] In one embodiment, to further improve the efficiency of problem solving and promote the progress of the meeting, please refer to Figure 2 , after step S50, further comprising: Step S60, determining whether to add conference participants.

[0072] In one embodiment, please refer to Figure 4 , step S60 may include: Step S601, collecting satisfaction evaluation information on the second predicted fault processing result, and calculating the satisfaction evaluation index as the second satisfaction evaluation index.

[0073] Step S602, determine whether the second satisfaction evaluation index is less than a preset second evaluation index threshold, if yes, proceed to step S603, if not, proceed to step S605.

[0074] Step S603, obtaining the fault handling result ranked first in the second predicted fault handling result, and obtaining the corresponding first conference participant information, and filtering out persons who are currently on duty but are not participants in the current meeting from the first conference participant information.

[0075] Step S604: initiate a conference push to the smart terminals where the screened personnel are located.

[0076] Step S605, end.

[0077] Based on step S601 to step S605, the efficiency of problem solving can be further improved and the meeting progress can be promoted by increasing the number of relevant meeting participants.

[0078] In one embodiment, the second evaluation index threshold may be equal to the first evaluation index threshold.

[0079] Although the problem finder and the meeting initiator are generally also among the meeting participants, in order to accurately record the meeting information, in one embodiment, based on the audio information and / or text information of the online meeting, the second meeting participant information is obtained and recorded. The second meeting participant information includes the problem finder and the meeting initiator.

[0080] Based on the method for obtaining the second predicted fault handling result of any of the above-mentioned embodiments, when the first predicted fault handling result is not satisfactory, and / or when no new solution is extracted within a preset time from the first predicted fault handling result, the second predicted fault handling result is initiated; on the basis of reducing the communication cost of fault meetings and improving communication efficiency, a certain amount of time is provided for personnel to accumulate fault handling experience, so as to generate new solutions and fault handling results, enrich the database, and provide more reserve solutions and experience for subsequent fault resolution.

[0081] In one embodiment of the present application, a computer-readable storage medium is provided, on which a program is stored. The stored program includes a method that can be loaded by a processor and process any one of the above embodiments.

[0082] Those skilled in the art will appreciate that all or part of the functions of the various methods in the above-mentioned embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to implement the above-mentioned functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above-mentioned functions can be implemented. In addition, when all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can also be stored in a storage medium such as a server, another computer, disk, optical disk, flash disk or mobile hard disk, and can be downloaded or copied and saved in the memory of the local device, or the system of the local device is updated, and when the program in the memory is executed by the processor, all or part of the functions in the above-mentioned embodiments can be implemented.

[0083] The above specific examples are used to illustrate the present invention, which is only used to help understand the present invention and is not intended to limit the present invention. For those skilled in the art, according to the concept of the present invention, some simple deductions, modifications or substitutions can be made.

Claims

1. A method for pushing conference solutions based on smart factories, characterized in that: include: Based on the audio information and / or text information of the online meeting, first conference participant information and first fault information are obtained in real time; The first conference participation information includes conference participants and conference content; The first fault information includes a fault object, fault data and a fault solution, and the fault data includes a fault type and a fault location; The first conference attendance information and the first fault information are used as inputs of a trained fault handling result prediction network, and a predicted fault handling result is obtained as a first predicted fault handling result; wherein the fault handling result includes a fault handling time and a fault handling cost; The first predicted fault processing result is displayed.

2. The conference solution push method according to claim 1, characterized in that: After displaying the first predicted fault processing result, the method further includes: Solution 1: Collect satisfaction evaluation information on the first predicted fault handling result, and calculate the satisfaction evaluation index as the first satisfaction evaluation index; if the first satisfaction evaluation index is less than the preset first evaluation index threshold, obtain at least one fault handling result based on the database as the second predicted fault handling result, and display the second predicted fault handling result and the corresponding first meeting information and first fault information; and / or, Solution 2: Calculate the duration from the start of display of the first predicted fault handling result to the current time in real time. If the duration reaches a preset first duration threshold, obtain at least one fault handling result based on the database as the second predicted fault handling result, and display the second predicted fault handling result and the corresponding first meeting information and first fault information. The database includes a plurality of fault handling information, each of which includes first meeting participation information, first fault information, and a fault handling result; the method of obtaining at least one fault handling result based on the database as the second predicted fault handling result includes: Based on the fault object and fault data, the corresponding fault handling result in the database is searched. If there are multiple fault handling results, the fault handling time less than the preset second time threshold is used as the first constraint condition, and the fault handling results that meet the first constraint condition are sorted from low to high according to the fault handling cost, and the previously set number of fault handling results are obtained as the second predicted fault handling result; or, the fault handling cost less than the preset first cost threshold is used as the second constraint condition, and the fault handling results that meet the second constraint condition are sorted from low to high according to the fault handling time, and the previously set number of fault handling results are obtained as the second predicted fault handling result.

3. The conference solution push method according to claim 2, characterized in that: After displaying the first predicted fault handling result, the method includes the case where the first satisfaction evaluation index is less than the preset first evaluation index threshold, obtaining at least one fault handling result based on the database as the second predicted fault handling result, including: If the first satisfaction evaluation index does not reach the preset first evaluation index threshold, the accuracy of the fault data is determined in response to the acquired monitoring data of the fault object. If the accuracy reaches the preset accuracy threshold, at least one fault processing result is obtained based on the database as the second predicted fault processing result.

4. The conference solution push method according to claim 2 or 3, characterized in that: After displaying the second predicted fault processing result, the method further includes: Collect satisfaction evaluation information on the second predicted fault handling result, and calculate the satisfaction evaluation index as the second satisfaction evaluation index; if the second satisfaction evaluation index is less than the preset second evaluation index threshold, obtain the fault handling result ranked first in the second predicted fault handling result, and obtain the corresponding first participant information, filter out personnel who are currently on duty but are not participants in the current meeting from the first participant information, and initiate a meeting push to the smart terminals where the filtered personnel are located.

5. The conference solution push method according to claim 4, characterized in that: The first fault prediction result is updated, including: In response to the updated first conference participant information and / or the first fault information, based on the trained fault processing result prediction network, updating the first predicted fault processing result; The updated first predicted fault processing result is displayed, and the updated display time is used as the start time of displaying the first predicted fault processing result.

6. The conference solution push method according to claim 5, characterized in that: Calculating an improvement value based on the updated first predicted fault processing result, and if the improvement value is greater than a preset value threshold, taking the fault solution corresponding to the updated first predicted fault processing result as a work result; The improvement value calculated based on the updated first predicted fault processing result includes a duration improvement value and / or a cost improvement value.

7. The conference solution push method according to claim 5, characterized in that: The calculation of the improvement value based on the updated first predicted fault processing result includes: K1=(A1-A2) / A1, B2≤B0, and / or, K2=(B1-B2) / B1, A2≤A0, Among them, K1 represents the cost improvement value, K2 represents the time improvement value, A1 represents the fault handling cost before improvement, A2 represents the fault handling cost after improvement, A0 represents the second cost threshold, B1 represents the fault handling time before improvement, B2 represents the fault handling time after improvement, and B0 represents the third time threshold.

8. The conference solution push method according to claim 3, characterized in that: The method further includes setting a first floating window and a second floating window; In response to the acquired first predicted fault processing result, displaying the first predicted fault processing result in a first floating window; In response to the acquired second predicted fault processing result, the second predicted fault processing result and the corresponding first conference participant information and first fault information are displayed in a second floating window.

9. The conference solution push method according to claim 1, characterized in that: The method also includes obtaining and recording second participant information based on audio information and / or text information of the online meeting; the second participant information includes the problem discoverer and the meeting initiator.

10. A computer-readable storage medium, characterized in that: The medium stores a program, which can be loaded by a processor and execute the conference solution pushing method as described in any one of claims 1 to 9.

Images