Conference data analysis method and device

Abstract

The invention discloses a conference data analysis method and device, and relates to the field of artificial intelligence and intelligent office, and the method comprises the steps: training a word segmentation dictionary according to historical issue data, and obtaining a historical word segmentation result; obtaining historical conference data corresponding to the historical issue data, and calculating conference participant data and conference participant data with the highest association degree of each historical word segmentation result according to a clustering algorithm; the method comprises the following steps: acquiring a newly input topic, performing word segmentation on the newly input topic to obtain a new word segmentation result, and outputting conference participant data and conference participant data which have the highest association degree with the new word segmentation result according to a historical word segmentation result matched with the new word segmentation result; and submitting participant data and participant data which have the highest association degree with the new word segmentation result, and respectively sending conference notifications to each participant according to different participant data. According to the invention, the system operation efficiency and the user working efficiency can be effectively improved, and the participants can be accurately and efficiently matched according to the issue.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence and smart office, and in particular to a conference data analysis method and device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] At present, most companies have their own conference systems. The pre-meeting preparation process is cumbersome, the workload is large, and the adaptability is lacking. In particular, senior executives in companies often attend multiple important meetings with different topics. When the meeting is held urgently, it is difficult for the meeting secretary to prepare the meeting topics and relevant participant information in time, which can easily cause the meeting progress to be slow and affect the work efficiency of the participants. There is no effective solution to this problem in the existing technology. Summary of the invention

[0004] The embodiment of the present invention provides a conference data analysis method for accurately and efficiently matching participants according to topics, improving work efficiency, and improving user experience. The method includes:

[0005] Obtain the topic data of historical meetings, train a word segmentation dictionary based on the topic data of historical meetings, and segment the topic data of historical meetings using the trained word segmentation dictionary to obtain historical word segmentation results;

[0006] Obtaining historical meeting attendance data corresponding to the topic data of historical meetings, wherein the historical meeting attendance data includes topic data, participant organization data, and participant data of historical meetings, and calculating the participant organization data and participant data with the highest correlation degree of each historical word segmentation result according to a clustering algorithm;

[0007] Acquire newly input conference topic data, perform word segmentation on the newly input conference topic data, obtain new word segmentation results, and match the new word segmentation results with historical word segmentation results;

[0008] After the match is successful, the data of participating organizations and participants with the highest correlation with the new segmentation results are determined based on the historical segmentation results that match the new segmentation results;

[0009] Verify the data of the participating organizations and participants that are most correlated with the new word segmentation results. After the verification is passed, send the meeting notification based on the data of the participating organizations and participants that are most correlated with the new word segmentation results.

[0010] The embodiment of the present invention also provides a conference data analysis device for accurately and efficiently matching participants according to topics, improving work efficiency, and improving user experience. The device includes:

[0011] The word segmentation module is used to obtain the topic data of historical meetings, train the word segmentation dictionary according to the topic data of historical meetings, and segment the topic data of historical meetings through the trained word segmentation dictionary to obtain the historical word segmentation results;

[0012] A participant calculation module is used to obtain historical meeting participant data corresponding to the topic data of historical meetings, wherein the historical meeting participant data includes topic data, participant organization data and participant data of historical meetings, and calculate the participant organization data and participant data with the highest correlation degree of each historical word segmentation result according to a clustering algorithm;

[0013] A matching module is used to obtain newly input conference topic data, segment the newly input conference topic data, obtain new segmentation results, and match the new segmentation results with historical segmentation results;

[0014] An output module is used to determine the participating organization data and participant data with the highest correlation with the new segmentation result based on the historical segmentation results that match the new segmentation result after the matching is successful;

[0015] The notification module is used to verify the data of the participating organizations and participants that are most correlated with the new word segmentation results. After the verification is passed, the conference notification is sent based on the data of the participating organizations and participants that are most correlated with the new word segmentation results.

[0016] An embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned conference data analysis method when executing the computer program.

[0017] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned conference data analysis method is implemented.

[0018] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned conference data analysis method is implemented.

[0019] In an embodiment of the present invention, topic data of historical meetings are obtained, a word segmentation dictionary is trained according to the topic data of historical meetings, and the topic data of historical meetings are segmented by the trained word segmentation dictionary to obtain historical word segmentation results; historical meeting participant data corresponding to the topic data of historical meetings are obtained, and the historical meeting participant data includes topic data, participant organization data and participant data of historical meetings, and according to a clustering algorithm, the participant organization data and participant data with the highest correlation of each historical word segmentation result are calculated; newly input conference topic data are obtained, and the newly input conference topic data are segmented to obtain new word segmentation results, and the new word segmentation results are matched with the historical word segmentation results; after the match is successful, the participant organization data and participant data with the highest correlation with the new word segmentation result are determined according to the historical word segmentation results that match the new word segmentation results; the participant organization data and participant data with the highest correlation with the new word segmentation result are verified, and after the verification is passed, a meeting notification is sent according to the participant organization data and participant data with the highest correlation with the new word segmentation result. In this way, by dividing the topics and establishing similar word segmentation tables and word segmentation index libraries, we can automatically match participating organizations and participants according to the conference topics, and then verify the output matching information. When the verification fails, we can directly modify the participating organization data and participant data. This allows us to accurately and efficiently match participants according to topics, improve work efficiency, and enhance user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0021] Figure 1 A flowchart of a conference data analysis method provided in an embodiment of the present invention;

[0022] Figure 2 An example diagram of calculating the highest correlation between the historical word segmentation results and the participant data provided in an embodiment of the present invention;

[0023] Figure 3 Another example diagram of calculating the highest correlation between the historical word segmentation results and the participant data provided in the embodiment of the present invention;

[0024] Figure 4 A schematic diagram of a conference data analysis device provided in an embodiment of the present invention;

[0025] Figure 5 It is a structural block diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0027] The term "and / or" herein only describes an association relationship, indicating that three relationships may exist. For example, A and / or B may represent the following three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set consisting of A, B, and C.

[0028] In the description of this specification, the terms "include", "including", "have", "contain", etc. are all open terms, which mean including but not limited to. The descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. mean that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps is not limited and can be appropriately adjusted as needed.

[0029] The embodiment of the present invention provides a conference data analysis method, such as Figure 1 As shown, including:

[0030] Step 101: Acquire the topic data of historical meetings, train a word segmentation dictionary based on the topic data of historical meetings, and segment the topic data of historical meetings using the trained word segmentation dictionary to obtain historical word segmentation results;

[0031] Step 102: Obtain historical meeting participant data corresponding to the topic data of the historical meeting, wherein the historical meeting participant data includes topic data, participant organization data, and participant data of the historical meeting, and calculate the participant organization data and participant data with the highest correlation degree of each historical word segmentation result according to a clustering algorithm;

[0032] Step 103: Acquire newly input conference topic data, perform word segmentation on the newly input conference topic data, obtain new word segmentation results, and match the new word segmentation results with historical word segmentation results;

[0033] Step 104: after the match is successful, the data of the participating organizations and the data of the participants with the highest correlation with the new segmentation results are determined according to the historical segmentation results that match the new segmentation results;

[0034] Step 105: Verify the data of the participating organization and the data of the participant that are most correlated with the new word segmentation result. After the verification is passed, send a meeting notice based on the data of the participating organization and the data of the participant that are most correlated with the new word segmentation result.

[0035] The conference data analysis method proposed in the embodiment of the present invention can automatically match the participating organizations through a three-layer efficient word segmentation algorithm, and then match the participants for the second time after matching the participating organizations. It supports users to manually modify and send the best match back to the system at the front desk, automatically classifies and generates conference notifications and arrangements, and can also recognize and judge information such as user leave, thereby improving system operation efficiency and user work efficiency, and improving user experience.

[0036] In the specific implementation, a word segmentation dictionary is established to segment all historical topic data, and all word segmentation results are saved as dictionary values ​​in the background database.

[0037] Figure 2 This is an example diagram of calculating the highest correlation between the historical segmentation results and the participant data provided in the embodiment of the present invention, such as Figure 2 As shown, in the embodiment of the present invention, according to the clustering algorithm, the data of the participating institutions and the data of the participants with the highest correlation of each historical word segmentation result are calculated, including:

[0038] Step 201: Divide the historical topic data into corresponding topics according to their meanings;

[0039] Step 202: Under each topic, a similar word meaning segmentation table corresponding to the topic is set, and a segmentation index library is established based on the most frequently used words in the similar word meaning segmentation table.

[0040] In a specific embodiment, according to the clustering algorithm, the data of the participating organizations and the data of the participants with the highest correlation degree among the historical word segmentation results are calculated, including:

[0041] Divide the historical topic data into corresponding topics according to their meanings;

[0042] Establish a word segmentation index library based on the most frequently used words in the similar word meaning segmentation table corresponding to each topic;

[0043] By querying the similar word meaning segmentation table, we can obtain the data of participating institutions with the highest correlation degree among the historical segmentation results;

[0044] By querying the word segmentation index library, the participant data with the highest correlation among the historical word segmentation results is obtained.

[0045] In specific implementation, according to the clustering algorithm, the information of the participating organizations and participants with the highest correlation with the word segments of the historical conference topics is calculated.

[0046] In a specific embodiment, the word segmentation rule library is divided into 10 topics according to the word meaning, and then a similar word segmentation table and a word segmentation index library are set under each topic. The words with the highest usage weight in the similar word segmentation table are taken to establish a word segmentation index library, as shown in Tables 1 and 2 below.

[0047] Table 1 Word segmentation index of participating institutions

[0048]

[0049] Table 2 Participants' Index Database

[0050]

[0051] In one embodiment, according to the historical word segmentation results that match the new word segmentation results, the participant organization data and participant data with the highest correlation with the new word segmentation results are determined, including:

[0052] The data of the participating institutions with the highest correlation with the historical word segmentation results that match the new word segmentation results are determined as the data of the participating institutions with the highest correlation with the new word segmentation results;

[0053] The participant data with the highest correlation degree with the historical word segmentation result matching the new word segmentation result is obtained, and the participant data is used as the participant data with the highest correlation degree with the new word segmentation result.

[0054] In one embodiment, after verifying the participant organization data and participant data with the highest correlation with the new word segmentation result, the method further includes:

[0055] After verification fails, modify the participating organization data and participant data.

[0056] In one embodiment, a conference notification is sent according to the data of the participating organization and the data of the participants that are most correlated with the new word segmentation result, including:

[0057] Meeting notices are sent in different ways based on the data of different participating organizations.

[0058] In one embodiment, according to different data of participating organizations, the conference notice is sent in different sending modes, including:

[0059] Modify the preset meeting notification template according to the data of different participating organizations;

[0060] Generate corresponding sending instructions based on the modified conference notification template corresponding to the data of different participating organizations.

[0061] Figure 3Another example diagram of calculating the highest correlation between the historical segmentation results and the participant data provided in the embodiment of the present invention is shown in FIG. Figure 3 As shown, in the embodiment of the present invention, according to the clustering algorithm, the data of the participating institutions and the data of the participants with the highest correlation of each historical word segmentation result are calculated, including:

[0062] Step 301: Matching topics based on historical topic data;

[0063] Step 302: After the historical topic data is successfully matched with the subject, the word segment with the closest meaning under the subject is matched according to the historical topic data;

[0064] Step 303: After the historical topic data is successfully matched with the word segmentation, the corresponding word segmentation index library is searched according to the most frequently used word in the similar word segmentation table, and the most relevant participating organization data and participant data are determined according to the corresponding word segmentation index library.

[0065] In specific implementation, words in the same similar word segmentation table are associated with the same word segmentation index. When matching, the subject is matched first, and then the word segmentation with the closest meaning under the subject is matched. After the match is successful, the specific rules in the word segmentation index rule library are found based on the most frequently used words in the similar word segmentation table. The three-layer word segmentation rule library is used to improve matching efficiency.

[0066] In a specific embodiment, the user inputs a topic, the system segments the topic, matches it with the words in the word segmentation dictionary, and outputs several word segmentation results if the match is successful. For example, after the word segmentation of "Digital Risk Control System Improvement Special Seminar", the result is "digital, risk control, system, improvement, special topic, seminar".

[0067] In one embodiment, based on the historical word segmentation results that match the new word segmentation results, the participant organization data and participant data with the highest correlation with the new word segmentation results are output, including:

[0068] Acquire the data of the participating institutions with the highest correlation with the historical word segmentation results that match the new word segmentation results, and use the data of the participating institutions as the data of the participating institutions with the highest correlation with the new word segmentation results;

[0069] The participant data with the highest correlation degree with the historical word segmentation result matching the new word segmentation result is obtained, and the participant data is used as the participant data with the highest correlation degree with the new word segmentation result.

[0070] In a specific embodiment, according to the word segmentation rule library, the reporter information corresponding to each of the six word segmentations is counted, including information such as reporting, learning leadership, communication, notification, reporting role, and reporting leader. For the reporting agency, the agency with the highest total number of reporting agencies of the six word segmentations is selected. If the reporting agencies corresponding to the six word segmentations are all different, the word with the highest number of appearances in the system is selected from the six word segmentations, and the corresponding reporting agency is the reporting agency for the topic. Similarly, the determination of information such as learning leadership, communication, notification, reporting role, and reporting leader is the same as reporting. According to this algorithm, the reporting, learning leadership, communication, notification, and reporting role information of the topic are determined.

[0071] The determined information on the report, leadership, communication, notification, and participating roles of the topic will be automatically displayed on the system front desk for user reference.

[0072] In one embodiment, according to the word segmentation and display results, the corresponding participants under the matching organization are automatically displayed on the system front desk for user reference. The conference secretary who created the conference topic receives the automatically matched participating organization and participant information on the front desk to confirm whether it is correct.

[0073] In one embodiment, verifying the participant organization data and participant data output according to the new word segmentation result includes:

[0074] After verification, submit the data of participating organizations and participants with the highest correlation with the new segmentation results;

[0075] After verification fails, modify the participating organization data and participant data.

[0076] In one embodiment, a modification number threshold is set;

[0077] In one verification, when the number of modifications to the participant organization data and participant data corresponding to a new word segmentation result reaches a modification number threshold, the participant organization data and participant data with the highest correlation to the historical word segmentation results corresponding to the new word segmentation result are modified.

[0078] In specific implementation, if it is correct, the conference secretary submits the flow. If it is incorrect, the conference secretary modifies the participant information and submits the flow. The background sets the dynamic parameter N. When the conference secretary modifies the participant involved in a certain word N times in the system at the same time, the word segmentation rule library can be dynamically adjusted.

[0079] In a specific embodiment, for example, the reporting agency with the highest total number of statistics for " / numbers / risk control / system / improvement / topic / symposium" is taken from the "office" of the participles of "numbers" and "risk control". The subsequent meeting secretary selects the reporting agency with the highest total number of statistics, and the reporting agency "office" taken from other topics of "numbers" and "risk control" is modified more than N times, then the reporting agency data corresponding to "numbers" and "risk control" in the database is modified.

[0080] For example, the reporting agency with the highest total number of statistics for “ / number / risk control / system / improvement / topic / discussion” is taken from the “office” of the “risk control” participle. The subsequent meeting secretary will select the reporting agency with the highest total number of statistics, and the reporting agency “office” is taken from other topics of “risk control”. If the number of modifications of the reporting agency “office” exceeds N times, then the reporting agency data corresponding to “risk control” in the database will be modified.

[0081] In one embodiment, according to different data of participating organizations, a conference notice is sent to each participant respectively, including:

[0082] Modify the preset meeting notice template;

[0083] Generate corresponding sending instructions based on meeting notification templates with different contents.

[0084] In specific implementation, there are multiple topics in a meeting, and some organizations only attend certain topics. For meetings with a high level of confidentiality, it is particularly important to protect the content of the meeting, and different meeting notices and arrangements need to be generated according to different participating organizations. The system can calculate according to the topics of the organization's participation, and automatically generate completely different meeting notices and arrangements for each organization, avoiding the need for the meeting secretary to manually classify, fill in and send them. New meeting notices and arrangements can also be manually uploaded after generation.

[0085] Here's how.

[0086] 1. First, modify the content that needs to be replaced in the template to ${key}:

[0087] Then query the meeting data and assemble it into a Map. For example, the Map of the meeting notice is as follows

[0088] {

[0089] meetingTheme: The first executive committee meeting

[0090] beginDate: March 8, 2023 (Monday) 6:30 p.m.

[0091] roomName:0520 Quyang Building

[0092] hostInfo:

[0093] Topic: (I) Topic 1\rReport: Party Office, Director Office

[0094] registEndTime: March 8, 2023 5:16 PM

[0095] confComment:

[0096] contactInfo:

[0097] Remark:1. Join the club in time\r2. Don't be late

[0098] nowDate: March 7, 2023

[0099] }

[0100] Finally, replace the data in the data Map into the template file one by one according to the Key value and save it to the specified directory.

[0101] 2. Generate sending scope logic

[0102] 1) Query all organizations participating in the current meeting and remove duplicate deptList;

[0103] 2) Query the current meeting topic and participating organizations topicDeptList;

[0104] 3) Traverse deptList and topicDeptList to remove duplicates of the same organization. When processing, concatenate the IDs of different topics that the same organization participates in and record them as topicCom (topics that the organization participates in), and put them in each object of deptList;

[0105] 4) Then traverse the organization set deptList and group the organizations participating in the same topic into a sending range, for example:

[0106] The topics that organization A participates in are topic 1 and topic 2, the topics that organization B participates in are topic 3, and the topics that organization C participates in are also topic 1 and topic 2. Then the assembled sending range is:

[0107] Institution A, Institution C;

[0108] Topic 1, Topic 2;

[0109] Institution B;

[0110] Topic three.

[0111] In one embodiment, it further includes:

[0112] Obtain attendees' leave information before sending meeting notifications, and filter out attendees who have already taken leave;

[0113] When a participant asks for leave after the meeting notice is sent, the participant who asks for leave is filtered out, and the participating organization to which the participant who asks for leave belongs is re-matched.

[0114] In specific implementation, the conference secretary confirms that the information is correct and submits the process, and the participants receive the meeting notice and arrangement of the relevant topics. The conference system can synchronize leave information. The system can filter out participants who have taken leave during the initial matching and match other participants. If a participant takes leave after sending the meeting notice and arrangement, the system will synchronize the leave information, re-match the participants of the participating organization, and simultaneously update all meeting notices and arrangements involving the participant, and issue a reprinting prompt. Participants attend the meeting on time according to the information of the meeting notice and arrangement.

[0115] The present invention also provides a conference data analysis device, as described in the following embodiments. Since the principle of the device to solve the problem is similar to that of the conference data analysis method, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0116] Figure 4 Schematic diagram of a conference data analysis device provided in an embodiment of the present invention, such as Figure 4 As shown, the device comprises:

[0117] The word segmentation module 401 is used to obtain the topic data of the historical meeting, train the word segmentation dictionary according to the topic data of the historical meeting, and segment the topic data of the historical meeting by using the trained word segmentation dictionary to obtain the historical word segmentation result;

[0118] The conference participant calculation module 402 is used to obtain the historical conference participant data corresponding to the topic data of the historical conference, wherein the historical conference participant data includes the topic data of the historical conference, the participant organization data and the participant data, and calculate the participant organization data and the participant data with the highest correlation degree of each historical word segmentation result according to the clustering algorithm;

[0119] The matching module 403 is used to obtain the newly input conference agenda data, perform word segmentation on the newly input conference agenda data, obtain a new word segmentation result, and match the new word segmentation result with the historical word segmentation result;

[0120] Output module 404 is used to determine the participant organization data and participant data with the highest correlation with the new segmentation result according to the historical segmentation result that matches the new segmentation result after the matching is successful;

[0121] The notification module 405 is used to verify the data of the participating organization and the data of the participant with the highest correlation with the new word segmentation result. After the verification is passed, the conference notification is sent according to the data of the participating organization and the data of the participant with the highest correlation with the new word segmentation result.

[0122] In one embodiment, the conference attendance calculation module 402 is specifically used for:

[0123] Divide the historical topic data into corresponding topics according to their meanings;

[0124] Under each topic, a similar word meaning segmentation table corresponding to the topic is set, and a segmentation index library is established based on the most frequently used words in the similar word meaning segmentation table.

[0125] In one embodiment, the conference attendance calculation module 402 is specifically used for:

[0126] Match topics based on historical issue data;

[0127] After the historical topic data is successfully matched to the topic, the word segment with the closest meaning under the topic is matched according to the historical topic data;

[0128] After the historical topic data is successfully matched and segmented, the corresponding segmentation index library is found based on the most frequently used words in the similar segmentation table, and the data of participating organizations and participants with the highest correlation are determined based on the corresponding segmentation index library.

[0129] In one embodiment, the output module 404 is specifically used for:

[0130] Acquire the data of the participating institutions with the highest correlation with the historical word segmentation results that match the new word segmentation results, and use the data of the participating institutions as the data of the participating institutions with the highest correlation with the new word segmentation results;

[0131] The participant data with the highest correlation degree with the historical word segmentation result matching the new word segmentation result is obtained, and the participant data is used as the participant data with the highest correlation degree with the new word segmentation result.

[0132] In one embodiment, the notification module 405 is specifically used for:

[0133] After verification, submit the data of participating organizations and participants with the highest correlation with the new segmentation results;

[0134] After verification fails, modify the participating organization data and participant data.

[0135] In one embodiment, the notification module 405 is specifically used to:

[0136] Set the modification count threshold;

[0137] In one verification, when the number of modifications to the participant organization data and participant data corresponding to a new word segmentation result reaches a modification number threshold, the participant organization data and participant data with the highest correlation to the historical word segmentation results corresponding to the new word segmentation result are modified.

[0138] In one embodiment, the notification module 405 is specifically used to:

[0139] Modify the preset meeting notice template;

[0140] Generate corresponding sending instructions based on meeting notification templates with different contents.

[0141] In one embodiment, a leave detection module is also included, which is specifically used to:

[0142] Obtain attendees' leave information before sending meeting notifications, and filter out attendees who have already taken leave;

[0143] When a participant asks for leave after the meeting notice is sent, the participant who asks for leave is filtered out, and the participating organization to which the participant who asks for leave belongs is re-matched.

[0144] Based on the above invention concept, Figure 5 As shown, the present invention also proposes a computer device 500, including a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and executable on the processor 520, wherein the processor 520 implements the aforementioned conference data analysis method when executing the computer program 530.

[0145] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned conference data analysis method is implemented.

[0146] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned conference data analysis method is implemented.

[0147] To summarize, in an embodiment of the present invention, the topic data of historical meetings are obtained, a word segmentation dictionary is trained according to the topic data of historical meetings, and the topic data of historical meetings are segmented by the trained word segmentation dictionary to obtain historical word segmentation results; the historical meeting participant data corresponding to the topic data of historical meetings are obtained, and the historical meeting participant data includes the topic data of historical meetings, the participant organization data and the participant data, and according to the clustering algorithm, the participant organization data and the participant data with the highest correlation degree of each historical word segmentation result are calculated; the newly input conference topic data are obtained, the newly input conference topic data are segmented to obtain new word segmentation results, and the new word segmentation results are matched with the historical word segmentation results; after the match is successful, the participant organization data and the participant data with the highest correlation degree with the new word segmentation result are determined according to the historical word segmentation results that match the new word segmentation results; the participant organization data and the participant data with the highest correlation degree with the new word segmentation result are verified, and after the verification is passed, a meeting notification is sent according to the participant organization data and the participant data with the highest correlation degree with the new word segmentation result. In this way, by dividing the topics and establishing similar word segmentation tables and word segmentation index libraries, we can automatically match participating organizations and participants according to the conference topics, and then verify the output matching information. When the verification fails, we can directly modify the participating organization data and participant data. This allows us to accurately and efficiently match participants according to topics, improve work efficiency, and enhance user experience.

[0148] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0149] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0150] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0151] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0152] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A conference data analysis method, characterized in that: include: Obtain the topic data of historical meetings, train a word segmentation dictionary based on the topic data of historical meetings, and segment the topic data of historical meetings using the trained word segmentation dictionary to obtain historical word segmentation results; Obtaining historical meeting attendance data corresponding to the topic data of historical meetings, wherein the historical meeting attendance data includes topic data, participant organization data, and participant data of historical meetings, and calculating the participant organization data and participant data with the highest correlation degree of each historical word segmentation result according to a clustering algorithm; Acquire newly input conference topic data, perform word segmentation on the newly input conference topic data, obtain new word segmentation results, and match the new word segmentation results with historical word segmentation results; After the match is successful, the data of participating organizations and participants with the highest correlation with the new segmentation results are determined based on the historical segmentation results that match the new segmentation results; Verify the data of the participating organizations and participants that are most correlated with the new word segmentation results. After the verification is passed, send the meeting notification based on the data of the participating organizations and participants that are most correlated with the new word segmentation results.

2. The method according to claim 1, characterized in that According to the clustering algorithm, the data of participating institutions and participants with the highest correlation among the historical word segmentation results are calculated, including: Divide the historical topic data into corresponding topics according to their meanings; Establish a word segmentation index library based on the most frequently used words in the similar word meaning segmentation table corresponding to each topic; By querying the similar word meaning segmentation table, we can obtain the data of participating institutions with the highest correlation degree among the historical segmentation results; By querying the word segmentation index library, the participant data with the highest correlation among the historical word segmentation results is obtained.

3. The method according to claim 1, characterized in that According to the historical word segmentation results that match the new word segmentation results, determine the participating organization data and participant data that are most correlated with the new word segmentation results, including: The data of the participating institutions with the highest correlation with the historical word segmentation results that match the new word segmentation results are determined as the data of the participating institutions with the highest correlation with the new word segmentation results; The participant data with the highest correlation degree to the historical word segmentation result matching the new word segmentation result is obtained, and the participant data is used as the participant data with the highest correlation degree to the new word segmentation result.

4. The method according to claim 1, characterized in that After verifying the data of participating organizations and participants that are most relevant to the new segmentation results, it also includes: After verification fails, modify the participating organization data and participant data.

5. The method according to claim 4, characterized in that Also includes: Set the modification count threshold; In one verification, when the number of modifications to the participant organization data and participant data corresponding to a new word segmentation result reaches a modification number threshold, the participant organization data and participant data with the highest correlation to the historical word segmentation results corresponding to the new word segmentation result are modified.

6. The method according to claim 1, characterized in that Send meeting notifications based on the data of participating organizations and participants that are most relevant to the new segmentation results, including: Meeting notices are sent in different ways based on the data of different participating organizations.

7. The method according to claim 6, characterized in that According to the data of different participating organizations, conference notices are sent in different ways, including: Modify the preset meeting notification template according to the data of different participating organizations; Generate corresponding sending instructions based on the modified conference notification template corresponding to the data of different participating organizations.

8. A conference data analysis device, characterized in that: include: The word segmentation module is used to obtain the topic data of historical meetings, train the word segmentation dictionary according to the topic data of historical meetings, and segment the topic data of historical meetings through the trained word segmentation dictionary to obtain the historical word segmentation results; A participant calculation module is used to obtain historical meeting participant data corresponding to the topic data of historical meetings, wherein the historical meeting participant data includes topic data, participant organization data and participant data of historical meetings, and calculate the participant organization data and participant data with the highest correlation degree of each historical word segmentation result according to a clustering algorithm; A matching module is used to obtain newly input conference topic data, segment the newly input conference topic data, obtain new segmentation results, and match the new segmentation results with historical segmentation results; An output module is used to determine the participating organization data and participant data with the highest correlation with the new segmentation result based on the historical segmentation results that match the new segmentation result after the matching is successful; The notification module is used to verify the data of the participating organizations and participants that are most correlated with the new word segmentation results. After the verification is passed, the conference notification is sent based on the data of the participating organizations and participants that are most correlated with the new word segmentation results.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images