Conference content storage method and system based on artificial intelligence

Abstract

The invention provides a conference content storage method and system based on artificial intelligence, and the method comprises the steps: obtaining a conference record which at least comprises video information and corresponding voice information, and recognizing a user in the video information and the voice information corresponding to the user; converting the voice information into text information, establishing a mapping relationship between the text information and a corresponding user, transmitting target data formed by the user, the text information to which the user belongs and the original conference record into a storage space, and creating a corresponding storage space according to a time axis; and according to the time axis, the video information and the voice information, encrypting the target data stored in each storage space, and finally achieving the purposes of efficiently storing the conference content and increasing the confidentiality of the conference content.

Description

Technical Field

[0001] The present invention belongs to the field of information storage, and in particular relates to a conference content storage method and system based on artificial intelligence. Background Art

[0002] In today's meeting scenarios, whether it is a business meeting, academic seminar or communication meeting within various organizations, a large amount of information content will be generated, including speeches by participants, documents on display, and clashes of opinions during discussions.

[0003] Traditional meeting content storage methods mainly rely on manual recording or simple audio and video recording, which is inefficient and prone to missing information. In addition, meeting content is usually stored manually directly on hardware devices or cloud servers, which increases the possibility of information leakage. Summary of the invention

[0004] Based on this, an embodiment of the present invention provides an artificial intelligence-based conference content storage method and system, which aims to efficiently store conference content while increasing the confidentiality of conference content.

[0005] A first aspect of an embodiment of the present invention provides a conference content storage method based on artificial intelligence, the method comprising:

[0006] Acquire a meeting record, the meeting record including at least video information and corresponding voice information, and identify a user in the video information and the voice information corresponding to the user;

[0007] Convert the voice information into text information, establish a mapping relationship between the text information and the corresponding user, and transfer the user, the text information belonging to the user, and the target data formed by the original meeting record into the storage space, wherein the text information includes the first text information directly converted from the voice information and the second text information with refined semantics obtained through natural language processing;

[0008] When the meeting record needs to be retrieved from the storage space, the second text information is matched according to the keyword. If the match is successful, the first text information corresponding to the second text information is determined, and then the corresponding voice information is determined according to the mapping relationship, and finally the corresponding video clip is found according to the voice information;

[0009] In the step of transferring the target data formed by the user, the text information belonging to the user and the original meeting record into the storage space, a corresponding storage space is created according to the timeline; and the target data stored in each storage space is encrypted according to the timeline, the video information and the voice information.

[0010] Furthermore, in the step of identifying the user in the video information and the voice information corresponding to the user, the user's facial information and timbre information are pre-established, and the user in the video information is identified based on the facial information, and the corresponding user is determined based on the timbre information.

[0011] Furthermore, the step of creating a corresponding storage space according to the time axis includes:

[0012] Obtaining a preset time axis, wherein the preset time axis includes a plurality of time periods, wherein the same time period in each day belongs to the same time axis;

[0013] A corresponding number of storage spaces are created according to the number of preset time axes, and each storage space is used to store data of the same time period on different dates.

[0014] Furthermore, the step of transferring the target data formed by the user, the text information belonging to the user and the original meeting record into the storage space includes:

[0015] According to the time period, the user, the text information belonging to the user and the original meeting record are segmented to obtain segmented data, and a connection between the segmented data is established, and the connection is used to splice the segmented data when the meeting record needs to be retrieved from the storage space;

[0016] The segmented data are transferred to the corresponding storage space for storage.

[0017] Furthermore, the step of encrypting the target data stored in each storage space according to the timeline, the video information and the voice information includes:

[0018] According to the sequence of time periods on the time axis and according to the video information and voice information stored in the time period, the target data stored in each storage space is encrypted in sequence.

[0019] Furthermore, the step of encrypting the target data stored in each storage space in sequence according to the sequence of time periods on the time axis and according to the video information and voice information stored in the time period includes:

[0020] When there are two time periods, the basic digital password is determined according to the first time period in the order;

[0021] Determine the names of the users who spoke based on the video information in the first time period, and sort the pinyin characters of the names according to the order in which the users spoke, wherein when the users speak at the same time, sort the pinyin characters of the corresponding user names according to their job levels;

[0022] According to the basic digital password, select corresponding characters in the sorting results to form a first password group;

[0023] Perform a hash operation on the first password group to obtain a first hash value, where the first hash value is an encrypted password for the data in the first period, and determine letters in the first hash value;

[0024] Obtaining first text information corresponding to the voice information in the second time period sorted later, converting the characters in the first text information into pinyin characters, and counting the number of letters in the first hash value in the pinyin characters converted from the characters in the first text information;

[0025] Substitute the number into the position of the letters in the first hash value, and perform a hash operation to obtain a second hash value, where the second hash value is the encryption password of the data in the second period;

[0026] The first Hash value and the second Hash value are combined, and a Hash operation is performed on the combined result to obtain a target Hash value, where the target Hash value is an encrypted password of the time axis.

[0027] A second aspect of an embodiment of the present invention provides an artificial intelligence-based conference content storage system, which is used to implement the artificial intelligence-based conference content storage method provided in the first aspect, and the system includes:

[0028] An identification module, used to obtain a conference record, the conference record at least including video information and corresponding voice information, and identify a user in the video information and the voice information corresponding to the user;

[0029] The input module is used to convert the voice information into text information, establish a mapping relationship between the text information and the corresponding user, and input the target data formed by the user, the text information belonging to the user and the original meeting record into the storage space, wherein the text information includes the first text information directly converted from the voice information and the second text information with refined semantics obtained through natural language processing.

[0030] A third aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the artificial intelligence-based conference content storage method provided in the first aspect.

[0031] A fourth aspect of an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the artificial intelligence-based conference content storage method provided in the first aspect is implemented.

[0032] An artificial intelligence-based conference content storage method and system are provided in an embodiment of the present invention. The method obtains conference records, which include at least video information and corresponding voice information, and identifies users in the video information and the voice information corresponding to the users; converts the voice information into text information, and establishes a mapping relationship between the text information and the corresponding users, and transmits the user, the text information belonging to the user, and the target data formed by the original conference record into a storage space, wherein a corresponding storage space is created according to a timeline; according to the timeline, the video information and the voice information, the target data stored in each storage space is encrypted, thereby ultimately achieving the purpose of efficiently storing conference content while increasing the confidentiality of the conference content. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A flowchart of an implementation method of a conference content storage method based on artificial intelligence provided in Embodiment 1 of the present invention;

[0034] Figure 2 A structural block diagram of a conference content storage system based on artificial intelligence provided in Embodiment 2 of the present invention;

[0035] Figure 3 This is a structural block diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0036] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0037] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0039] Embodiment 1

[0040] According to an embodiment of the present invention, a conference content storage method based on artificial intelligence is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0041] In this embodiment 1, a conference content storage method based on artificial intelligence is provided, which can be used in electronic devices, such as computers. Figure 1 , Figure 1 The flowchart of an implementation method of a conference content storage method based on artificial intelligence provided in the first embodiment of the present invention is shown, which specifically includes steps S01 to S02.

[0042] Step S01, obtaining a meeting record, wherein the meeting record includes at least video information and corresponding voice information, and identifying a user in the video information and the voice information corresponding to the user.

[0043] Specifically, the meeting can be recorded through a camera with a recording function set up in the conference venue. It should be noted that in order to identify the user in the video information and the user's corresponding voice information, the user's facial information and timbre information are established in advance, and the user in the video information is identified based on the facial information. At the same time, the corresponding user is determined based on the timbre information, that is, what each person says is recorded accordingly.

[0044] Step S02, converting the voice information into text information, and establishing a mapping relationship between the text information and the corresponding user, and transferring the target data formed by the user, the text information belonging to the user and the original meeting record into the storage space.

[0045] Among them, the text information includes first text information directly converted from the voice information and second text information with refined semantics obtained through natural language processing. It can be understood that the words recorded in the first text information are what the user said. In addition, the second text information is obtained by processing the semantic information of the text through a deep learning model of the Transformer architecture (such as BERT, GPT series), which facilitates quick search of meeting records.

[0046] It should be noted that when it is necessary to retrieve meeting minutes from the storage space, the second text information is matched according to the keywords. If the match is successful, the first text information corresponding to the second text information is determined, and then the corresponding voice information is determined according to the mapping relationship, and finally the corresponding video clip is found according to the voice information.

[0047] In this embodiment, in the step of transmitting the target data formed by the user, the text information to which the user belongs, and the original meeting record into the storage space, according to the time axis, a corresponding storage space is created. Specifically, a preset time axis is obtained. The preset time axis includes several time periods, where the same time periods in each day belong to the same time axis. Exemplarily, 24 preset time axes are set. It can be understood that in the first preset time axis, it includes the time period from 0:00 to 1:00 every day. In the second preset time axis, it includes the time period from 1:00 to 2:00 every day. In the third preset time axis, it includes the time period from 2:00 to 3:00 every day, and so on. In the 24th preset time axis, it includes the time period from 23:00 to 24:00 every day.

[0048] According to the number of preset time axes, a corresponding number of storage spaces are created. Each of the storage spaces is used to store data of the same time period on different dates.

[0049] More specifically, the step of transmitting the target data formed by the user, the text information to which the user belongs, and the original meeting record into the storage space includes:

[0050] According to the time period, the user, the text information to which the user belongs, and the original meeting record are segmented to obtain the segmented data, and the connection of each segmented data is established. The connection is used to splice each segmented data when the meeting record needs to be retrieved from the storage space;

[0051] The segmented data are respectively transmitted into the corresponding storage spaces for storage.

[0052] According to the time axis, video information, and voice information, the target data stored in each storage space is encrypted. Among them, according to the order of the time periods on the time axis, and according to the video information and voice information stored in the time period, the target data stored in each storage space is encrypted in sequence. Specifically, when the number of time periods is two, the basic digital password is determined according to the first time period sorted in front. The basic digital password can be automatically generated randomly after being triggered;

[0053] According to the video information in the first time period, the name of the speaking user is determined. According to the speaking order of the users, the pinyin characters of each name are sorted. For example, for "Zhang San" and "Li Si", according to the speaking order, the sorting result may be "zhangsanlisi". Among them, when there is a situation where users speak simultaneously, according to the rank of the users, the pinyin characters of the corresponding user names are sorted;

[0054] According to the basic digital password, corresponding characters are selected from the sorting results to form a first password group. For example, if the basic digital password is "1387945234", according to the sorting result "zhangsanlisi", the first password group is "zanalnghan". It should be noted that when the characters of the sorting result are short, the sorting results are cyclically combined. For example, if the sorting result is "lisi", the cyclic combination is "lisilisilisi...";

[0055] Perform a first hash operation based on SHA-3 on the first password group to obtain a first hash value, where the first hash value is an encrypted password for the data in the first period, and determine the letters in the first hash value;

[0056] Obtain the first text information corresponding to the voice information in the second time period sorted later, convert the text in the first text information into pinyin characters, and count the number of pinyin characters converted from the letters in the first hash value in the first text information. For example, if there is "a" among the letters in the first hash value, determine the number of pinyin characters converted from the text in the first text information;

[0057] Replace the number with the position of the letter in the first hash value, and perform a second hash operation based on SHA-3 to obtain a second hash value, where the second hash value is the encryption password of the data in the second period;

[0058] The first Hash value and the second Hash value are combined, and the combined result is subjected to a third Hash operation to obtain a target Hash value, where the target Hash value is the encryption password of the time axis.

[0059] It should be noted that when the number of time periods exceeds two, the first hash operation and the second hash operation are performed in a loop, and after the hash values ​​are obtained respectively, they are combined and the third hash operation is performed to obtain the encryption password of the corresponding time axis.

[0060] In summary, the artificial intelligence-based conference content storage method in the above-mentioned embodiment of the present invention obtains the conference record, which includes at least video information and corresponding voice information, and identifies the user in the video information and the voice information corresponding to the user; converts the voice information into text information, and establishes a mapping relationship between the text information and the corresponding user, and transmits the user, the text information belonging to the user, and the target data formed by the original conference record into the storage space, wherein, according to the timeline, the corresponding storage space is created; according to the timeline, the video information and the voice information, the target data stored in each storage space is encrypted, thereby ultimately achieving the purpose of efficiently storing the conference content while increasing the confidentiality of the conference content.

[0061] Embodiment 2

[0062] See also Figure 2 , Figure 2 This is a structural block diagram of an artificial intelligence-based conference content storage system provided in Embodiment 2 of the present invention. The artificial intelligence-based conference content storage system 200 is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0063] Specifically, the conference content storage system 200 based on artificial intelligence includes: an identification module 21 and an input module 22, wherein:

[0064] The recognition module 21 is used to obtain the conference record, which includes at least video information and corresponding voice information, and recognize the user in the video information and the voice information corresponding to the user, wherein the user's facial information and voice information are pre-established, and the user in the video information is recognized based on the facial information, and the corresponding user is determined based on the voice information;

[0065] The input module 22 is used to convert the voice information into text information, establish a mapping relationship between the text information and the corresponding user, and input the target data formed by the user, the text information belonging to the user, and the original meeting record into the storage space, wherein the text information includes the first text information directly converted from the voice information and the second text information with refined semantics obtained through natural language processing;

[0066] When the meeting record needs to be retrieved from the storage space, the second text information is matched according to the keyword. If the match is successful, the first text information corresponding to the second text information is determined, and then the corresponding voice information is determined according to the mapping relationship, and finally the corresponding video clip is found according to the voice information;

[0067] In the step of transferring the target data formed by the user, the text information belonging to the user and the original meeting record into the storage space, a corresponding storage space is created according to the timeline; and the target data stored in each storage space is encrypted according to the timeline, the video information and the voice information.

[0068] Further, in some optional embodiments of the present invention, the input module 22 includes:

[0069] An acquisition unit, used for acquiring a preset time axis, wherein the preset time axis includes a plurality of time periods, wherein the same time period in each day belongs to the same time axis;

[0070] The creation unit is used to create a corresponding number of storage spaces according to the number of preset time axes, and each storage space is used to store data of the same time period on different dates.

[0071] Furthermore, in some optional embodiments of the present invention, the input module 22 further includes:

[0072] A segmentation unit, for segmenting the user, the text information to which the user belongs, and the original meeting record according to the time period, to obtain segmented data, and to establish a connection between the segmented data, wherein the connection is used to splice the segmented data when the meeting record needs to be retrieved from the storage space;

[0073] The input unit is used to input the segmented data into corresponding storage spaces for storage.

[0074] Furthermore, in some optional embodiments of the present invention, the input module 22 further includes:

[0075] The encryption unit is used to encrypt the target data stored in each storage space in sequence according to the sequence of time periods on the time axis and according to the video information and voice information stored in the time period.

[0076] Further, in some optional embodiments of the present invention, the encryption unit includes:

[0077] The first determination subunit is used to determine the basic digital password according to the first time period which is ranked first when the number of time periods is two;

[0078] a sorting subunit, configured to determine the names of the users who spoke according to the video information in the first time period, and sort the pinyin characters of the names according to the order in which the users spoke, wherein when the users speak at the same time, the pinyin characters of the corresponding user names are sorted according to their job levels;

[0079] A selection subunit, configured to select corresponding characters from the sorting results according to the basic digital password to form a first password group;

[0080] A first operator unit is configured to perform a hash operation on the first password group to obtain a first hash value, where the first hash value is an encrypted password for the data in the first period, and determine letters in the first hash value;

[0081] a counting subunit, configured to obtain first text information corresponding to the voice information in the second time period sorted later, convert the characters in the first text information into pinyin characters, and count the number of letters in the first hash value in the pinyin characters converted from the characters in the first text information;

[0082] A second operator unit is used to replace the number with the position of the letters in the first hash value, and perform a hash operation to obtain a second hash value, where the second hash value is an encryption password for the data in the second period;

[0083] The third operator unit is used to combine the first Hash value and the second Hash value, and perform a Hash operation on the combined result to obtain a target Hash value, where the target Hash value is an encrypted password of the time axis.

[0084] Embodiment 3

[0085] Another aspect of the present invention provides an electronic device, see Figure 3 , shown is an electronic device in Embodiment 3 of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, the conference content storage method based on artificial intelligence as described above is implemented.

[0086] In some embodiments, the processor 10 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 20, such as executing access restriction programs.

[0087] Among them, the memory 20 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. The memory 20 may be an internal storage unit of an electronic device in some embodiments, such as a hard disk of the electronic device. The memory 20 may also be an external storage device of an electronic device in other embodiments, such as a plug-in hard disk equipped on the electronic device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Further, the memory 20 may also include both an internal storage unit and an external storage device of the electronic device. The memory 20 may be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or is to be output.

[0088] It should be pointed out that Figure 3 The structure shown does not constitute a limitation on the electronic device. In other embodiments, the electronic device may include fewer or more components than those shown in the figure, or combine certain components, or arrange the components differently.

[0089] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the conference content storage method based on artificial intelligence as described above is implemented.

[0090] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0091] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0092] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0093] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0094] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.

Claims

1. A conference content storage method based on artificial intelligence, characterized in that: The method comprises: Acquire a meeting record, the meeting record including at least video information and corresponding voice information, and identify a user in the video information and the voice information corresponding to the user; Convert the voice information into text information, establish a mapping relationship between the text information and the corresponding user, and transfer the user, the text information belonging to the user, and the target data formed by the original meeting record into the storage space, wherein the text information includes the first text information directly converted from the voice information and the second text information with refined semantics obtained through natural language processing; When the meeting record needs to be retrieved from the storage space, the second text information is matched according to the keyword. If the match is successful, the first text information corresponding to the second text information is determined, and then the corresponding voice information is determined according to the mapping relationship, and finally the corresponding video clip is found according to the voice information; In the step of transferring the target data formed by the user, the text information belonging to the user and the original meeting record into the storage space, a corresponding storage space is created according to the timeline; and the target data stored in each storage space is encrypted according to the timeline, the video information and the voice information.

2. The method for storing conference content based on artificial intelligence according to claim 1, characterized in that: In the step of identifying the user in the video information and the voice information corresponding to the user, the user's facial information and timbre information are pre-established, and the user in the video information is identified based on the facial information, and the corresponding user is determined based on the timbre information.

3. The method for storing conference content based on artificial intelligence according to claim 2, characterized in that: The step of creating a corresponding storage space according to the time axis includes: Obtaining a preset time axis, wherein the preset time axis includes a plurality of time periods, wherein the same time period in each day belongs to the same time axis; A corresponding number of storage spaces are created according to the number of preset time axes, and each storage space is used to store data of the same time period on different dates.

4. The method for storing conference content based on artificial intelligence according to claim 3, characterized in that: The step of transferring the target data formed by the user, the text information of the user and the original meeting record into the storage space comprises: According to the time period, the user, the text information belonging to the user and the original meeting record are segmented to obtain segmented data, and a connection between the segmented data is established, and the connection is used to splice the segmented data when the meeting record needs to be retrieved from the storage space; The segmented data are transferred to the corresponding storage space for storage.

5. The method for storing conference content based on artificial intelligence according to claim 4, characterized in that: The step of encrypting the target data stored in each storage space according to the timeline, the video information and the voice information comprises: According to the sequence of time periods on the time axis and according to the video information and voice information stored in the time period, the target data stored in each storage space is encrypted in sequence.

6. The method for storing conference content based on artificial intelligence according to claim 5, characterized in that: The step of encrypting the target data stored in each storage space in sequence according to the sequence of time periods on the time axis and according to the video information and voice information stored in the time period comprises: When there are two time periods, the basic digital password is determined according to the first time period in the order; Determine the names of the users who spoke based on the video information in the first time period, and sort the pinyin characters of the names according to the order in which the users spoke, wherein when the users speak at the same time, sort the pinyin characters of the corresponding user names according to their job levels; According to the basic digital password, select corresponding characters in the sorting results to form a first password group; Perform a hash operation on the first password group to obtain a first hash value, where the first hash value is an encrypted password for the data in the first period, and determine letters in the first hash value; Obtaining first text information corresponding to the voice information in the second time period sorted later, converting the characters in the first text information into pinyin characters, and counting the number of letters in the first hash value in the pinyin characters converted from the characters in the first text information; Substitute the number into the position of the letters in the first hash value, and perform a hash operation to obtain a second hash value, where the second hash value is the encryption password of the data in the second period; The first Hash value and the second Hash value are combined, and a Hash operation is performed on the combined result to obtain a target Hash value, where the target Hash value is an encrypted password of the time axis.

7. A conference content storage system based on artificial intelligence, characterized in that: For implementing the conference content storage method based on artificial intelligence according to any one of claims 1 to 6, the system comprises: An identification module, used to obtain a conference record, the conference record at least including video information and corresponding voice information, and identify a user in the video information and the voice information corresponding to the user; The input module is used to convert the voice information into text information, establish a mapping relationship between the text information and the corresponding user, and input the target data formed by the user, the text information belonging to the user and the original meeting record into the storage space, wherein the text information includes the first text information directly converted from the voice information and the second text information with refined semantics obtained through natural language processing.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the conference content storage method based on artificial intelligence as described in any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for storing conference content based on artificial intelligence as described in any one of claims 1 to 6 is implemented.

Images