A cultural relic identification and explanation system based on generative artificial intelligence

Abstract

The present invention discloses a cultural relic identification and explanation system based on generative artificial intelligence, including an identification module, a sound input module, a sound output module, a conversion module, a data platform and a hardware module, wherein the identification module scans and identifies cultural relics, the sound input module is used to obtain the sound information of the user, the conversion module converts the picture information of the identification module and the audio information of the sound input module into text information, the conversion module inputs the text information into a data platform, the data platform retrieves the cultural relic information according to the text description, the data platform is connected to the artificial intelligence platform through a network, and the sound output module outputs the information retrieved by the data platform. After using the identification module and the sound input module, the data platform is connected to the artificial intelligence platform, and real-time explanations and replies are made through the cultural relics observed by the user and the questions asked, thereby improving the interactivity and convenience of use of the cultural relic identification and explanation system.

Description

Technical Field

[0001] The invention belongs to the technical field of explanation systems and relates to a cultural relic identification and explanation system based on generative artificial intelligence. Background Art

[0002] Cultural relics are witnesses of history. By understanding cultural relics, we can understand the history and culture of the era in which they are located. Cultural relics are mostly stored in museums. Cultural relics themselves are just objects. Their cultural connotations need to be understood through explanations in combination with books and other materials. Many museums today are equipped with tour guides and electronic explanation systems.

[0003] The current electronic explanation system has a relatively simple explanation format, poor interactivity, and requires manual operation to select cultural relics for introduction, which makes it inconvenient to use. Summary of the invention

[0004] In view of the above problems, the present invention proposes a cultural relics identification and explanation system based on generative artificial intelligence, which well solves the problems in the prior art.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A cultural relic identification and explanation system based on generative artificial intelligence, comprising:

[0007] An identification module, which scans and identifies cultural relics;

[0008] A voice input module, which is used to obtain voice information of the user;

[0009] A conversion module, which converts the image information of the recognition module and the audio information of the sound input module into text information;

[0010] A data platform, wherein the conversion module inputs text information into the data platform, and the data platform retrieves cultural relic information based on the text description;

[0011] A sound output module, the sound output module outputs the information retrieved by the data platform;

[0012] A hardware module, wherein the recognition module, the sound input module, the sound output module, the conversion module and the data platform are all arranged in the hardware module;

[0013] Wherein, the data platform is connected to the artificial intelligence platform via a network.

[0014] Optionally, the hardware module includes:

[0015] A first platform, wherein the first platform is a head-mounted support;

[0016] A visual sensor, wherein the visual sensor provides data for the recognition module;

[0017] A sound receiving component, the sound receiving component provides data for the sound input module;

[0018] A playing component, wherein the playing component plays the sound output module data;

[0019] A second platform, the data platform and the conversion module are arranged on the second platform;

[0020] Wherein, the visual sensor, the sound collecting component and the playing component are all installed on the first platform;

[0021] A Bluetooth module, both the first platform and the second platform are provided with the Bluetooth module, and data is exchanged through the Bluetooth module;

[0022] A display module is provided on the second platform, and the second platform has a built-in exhibition hall map.

[0023] Optionally, the first platform is equipped with a position indicating light source, and the position indicating light source is installed at the position of the visual sensor, and the position indicating light source indicates the current scanning position of the visual sensor through a light spot.

[0024] Optionally, a keyword recognition module is further included. The conversion module receives the information from the sound input module and inputs it into the keyword recognition module. The keyword recognition module recognizes the keyword and activates the visual sensor.

[0025] Optionally, the first platform is a glasses frame, and the visual sensor, sound collecting component, and playback component can be detachably installed on the first platform.

[0026] Optionally, the visual sensor, the sound collecting component, and the playing component are fixedly connected to the same mounting plate, the mounting plate is fixedly mounted with a C-shaped clip, and the C-shaped clip is mounted on the first platform.

[0027] Optionally, the conversion module is connected to an identification database, the identification database stores information on the sensitivity of cultural relics to light sources, and the identification module is connected to the position-indicating light source signal.

[0028] Optionally, the sound collecting component is a bone conduction sound collecting component.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] 1. After using the recognition module and the sound input module, the data platform is connected to the artificial intelligence platform to make real-time explanations and responses based on the cultural relics observed and questions asked by users, thereby improving the interactivity and convenience of the cultural relics identification and explanation system;

[0031] 2. The first platform is set as a head-mounted bracket, which makes it easier for the visual sensor part to follow the user's head rotation and obtain the information of the cultural relics that the user is observing. Different modules are set on the first platform and the second platform to reduce the wearing weight of the first platform and improve the comfort of use. At the same time, when setting up the second platform, the data platform and the conversion module part and the artificial intelligence platform that needs to call data can be set as small programs, which can be downloaded and used through the user's mobile phone and other electronic devices, further reducing the use cost and wearing weight, and improving the comfort of use;

[0032] 3. When exhibiting cultural relics, smaller cultural relics may be displayed together, and the cultural relics that need to be explained may be illuminated and marked by a position-indicating light source, so that the visual sensor can select the part that the user needs to explain from the acquired data. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic diagram of the module structure of an embodiment of the present invention;

[0034] Figure 2 It is a structural schematic diagram of the first platform of an embodiment of the present invention.

[0035] Reference numerals: 1. identification module; 11. identification database;

[0036] 21. Sound input module; 22. Sound output module;

[0037] 3. Conversion module; 31. Keyword recognition module;

[0038] 4. Data platform;

[0039] 5. Hardware module; 51. First platform; 511. Mounting plate; 512. C-type clip; 52. Visual sensor; 53. Sound receiving component; 54. Playing component; 55. Position indicating light source;

[0040] 6. Bluetooth module. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] See also Figure 1, is a cultural relic identification and explanation system based on generative artificial intelligence disclosed in an embodiment of the present invention, comprising a recognition module 1, a sound input module 21, a sound output module 22, a conversion module 3, a data platform 4 and a hardware module 5, wherein the recognition module 1 scans and identifies the cultural relics, the sound input module 21 is used to obtain the sound information of the user, the conversion module 3 converts the picture information of the recognition module 1 and the audio information of the sound input module 21 into text information, the conversion module 3 inputs the text information into the data platform 4, the data platform 4 retrieves the cultural relic information according to the text description, the data platform 4 is connected to the artificial intelligence platform through the network, the sound output module 22 outputs the information retrieved by the data platform 4, and the recognition module 1, the sound input module 21, the sound output module 22, the conversion module 3 and the data platform 4 are all arranged in the hardware module 5.

[0043] Specifically, the recognition module 1 and the sound input module 21 are installed in the hardware module 5, and the visual recognition data and audio data are converted into text descriptions through the conversion module 3. The text descriptions enter the data platform 4 connected to the artificial intelligence platform, and after feedback is obtained, they are fed back to the user through the sound output module 22.

[0044] In this way, after using the recognition module 1 and the sound input module 21, the data platform 4 is connected to the artificial intelligence platform, and real-time explanations and responses are made based on the cultural relics observed and questions asked by the user, thereby improving the interactivity and ease of use of the cultural relic identification and explanation system.

[0045] In some feasible ways, the recognition module 1 obtains the information of the cultural relics through visual recognition technology, the conversion module 3 corresponds its information to the name of the cultural relic and other information, and transmits the information to the data platform 4. The data platform 4 is connected to the artificial intelligence platform. The artificial intelligence platform can be a generative artificial intelligence platform such as ChatGPT. After the data platform 4 is connected, the question is input into the artificial intelligence platform, and the answer of the artificial intelligence platform is obtained for broadcasting, thereby reducing development costs.

[0046] See also Figure 1 and Figure 2 As a specific implementation of a cultural relic identification and explanation system based on generative artificial intelligence provided in the application, the hardware module 5 includes a first platform 51 and a second platform. The first platform 51 is a head-mounted bracket. The first platform 51 is equipped with a visual sensor 52, a sound collecting component 53 and a playback component 54. The visual sensor 52 provides data for the identification module 1, the sound collecting component 53 provides data for the sound input module 21, and the playback component 54 plays the data of the sound output module 22. The data platform 4 and the conversion module 3 are arranged on the second platform. The first platform 51 and the second platform are both provided with a Bluetooth module 6, and data exchange and positioning are carried out through the Bluetooth module 6. A display module is arranged on the second platform, and the second platform has a built-in exhibition hall map.

[0047] In general, setting the first platform 51 as a head-mounted bracket makes it easier for the visual sensor 52 to follow the rotation of the user's head to obtain information about the cultural relics the user is observing. Different modules are separated on the first platform 51 and the second platform to reduce the wearing weight of the first platform 51 and improve the comfort of use.

[0048] At the same time, when setting up the second platform, the recognition module 1, the conversion module 3, the data platform 4 and the artificial intelligence platform that needs to call data can be set as small programs, which can be downloaded and used through the user's mobile phone and other electronic devices, further reducing the use cost and wearing weight, and improving the comfort of use. The museum map is built into the second platform, and the locations of the cultural relics are numbered. When the first platform 51 recognizes the cultural relics, the Bluetooth module 6 synchronizes the number to the second platform, marks the location of the cultural relics through the second platform, and displays it through the display module, so that visitors can clearly identify their location.

[0049] In some feasible embodiments, the first platform 51 is configured as a glasses frame, the playback component 54 and the sound collection component 53 are respectively a Bluetooth headset and a microphone, and the visual sensor 52 can be installed in the middle of the first platform 51, so that the visual sensor 52 can better follow the user's observation object. In order to facilitate adaptation to more users, the visual sensor 52, the sound collection component 53, and the playback component 54 are fixedly connected to the same mounting plate 511, and the mounting plate 511 is fixedly installed with a C-type clip 512, and the C-type clip 512 includes two elastic buckles. The C-type clip 512 is installed on the first platform 51. Through the detachable setting, the user can place different components on his or her glasses to further improve the comfort of use. The mounting plate 511 is a rectangular plate or a rectangular box, and the visual sensor 52, the sound collection component 53, the playback component 54, the power supply battery and the Bluetooth module 6 are all installed on the mounting plate 511. The mounting plate 511 is clamped on the glasses leg through the C-type clip 512. In order to maintain the balance of wearing, the weight can also be distributed on the two glasses legs through the two mounting plate 511 parts.

[0050] Furthermore, the first platform 51 is installed with a position indicating light source 55, which is installed at the position of the visual sensor 52. The position indicating light source 55 indicates the current scanning position of the visual sensor 52 through a light spot.

[0051] In combination with specific usage scenarios, when exhibiting cultural relics, smaller cultural relics may be displayed together, and the cultural relics that need to be explained are illuminated and marked by the position indicating light source 55, so that the visual sensor 52 can select the part that the user needs to explain from the acquired data.

[0052] When in use, the intensity and color of the position indicating light source 55 should be set according to the protection needs of the cultural relics. When some cultural relics cannot be irradiated by light sources such as lasers, the position indicating light source 55 should be turned off. To avoid damaging the cultural relics, the conversion module 3 is connected to the recognition database 11, which stores the sensitivity information of the cultural relics to the light source. The recognition module 1 is connected to the position indicating light source 55 signal.

[0053] It should be understood that by identifying the information in the database 11, after the data of the identification module 1 is transmitted, the information in the identification database 11 is matched, and the positioning light source 55 is selected not to be turned on for the cultural relics that cannot be illuminated. When the identification module 1 has not completed the identification, the positioning light source 55 should be in a normally closed state.

[0054] When in use, the visual sensor 52 photographs and identifies the cultural relics, and the identification database 11 turns on the positioning light source 55 after identification. The user turns the head to aim the positioning light source 55 at the cultural relics that need to be explained, so as to facilitate accurate explanation. The cultural relics are usually provided with labels. When it is not appropriate to turn on the positioning light source 55 after identification by the identification database 11, voice inquiries can also be made through the sound collection component 53.

[0055] Furthermore, it also includes a keyword recognition module 31 . The conversion module 3 receives information from the sound input module 21 and inputs the information into the keyword recognition module 31 . The keyword recognition module 31 recognizes the keyword and activates the visual sensor 52 .

[0056] In combination with specific usage scenarios, the visual sensor 52, the sound collecting component 53, the playback component 54 and the Bluetooth module 6 all need to be powered by batteries. After setting the keyword recognition module 31, the user audio recorded by the keyword recognition module 31 is compared, and then the visual sensor 52 is started. After the cultural relic recognition is completed and the data is transmitted to the conversion module 3, it is turned off to reduce power consumption and increase the use time of the device. At the same time, it can also be started by keywords to improve the interactivity between users and devices.

[0057] In some feasible ways, the keywords of the keyword recognition module 31 are set by the user, such as a temporary name given to the cultural relic recognition and interpretation system, or a standard query sentence, etc., to improve the interactivity between the user and the device.

[0058] As another specific implementation of a cultural relic identification and interpretation system based on generative artificial intelligence provided in the application, the sound collecting component 53 is a bone conduction sound collecting component.

[0059] Combined with the specific usage scenario, during the peak period of visiting cultural relics, there are many visitors, which will cause great interference to the sound collection component 53. By setting up bone conduction sound collection, the vibration of the head and neck bones of the user when speaking is used to collect the sound, thereby reducing the mutual interference of different users' voices. At the same time, the playback component 54 adopts the form of ordinary headphones, which can transmit sound and play a certain role in isolating external sounds.

[0060] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A cultural relic identification and explanation system based on generative artificial intelligence, characterized in that: include: An identification module (1), wherein the identification module (1) scans and identifies cultural relics; A voice input module (21), the voice input module (21) is used to obtain voice information of a user; A conversion module (3), wherein the conversion module (3) converts the image information of the recognition module (1) and the audio information of the sound input module (21) into text information; A data platform (4), wherein the conversion module (3) inputs the text information into the data platform (4), and the data platform (4) retrieves the cultural relic information according to the text description; A sound output module (22), the sound output module (22) outputs the information retrieved by the data platform (4); A hardware module (5), wherein the recognition module (1), the sound input module (21), the sound output module (22), the conversion module (3) and the data platform (4) are all arranged in the hardware module (5); Wherein, the data platform (4) is connected to the artificial intelligence platform via a network.

2. The cultural relics identification and explanation system based on generative artificial intelligence according to claim 1, characterized in that: The hardware module (5) comprises: A first platform (51), wherein the first platform (51) is a head-mounted support; A visual sensor (52), the visual sensor (52) providing data for the recognition module (1); a sound receiving component (53), wherein the sound receiving component (53) provides data for the sound input module (21); A playing component (54), the playing component (54) plays the data of the sound output module (22); A second platform, the data platform (4) and the conversion module (3) are arranged on the second platform; Wherein, the visual sensor (52), the sound collecting component (53) and the playing component (54) are all installed on the first platform (51); A Bluetooth module (6), the first platform (51) and the second platform are both provided with the Bluetooth module (6), and data is exchanged via the Bluetooth module (6); A display module is provided on the second platform, and the second platform has a built-in exhibition hall map.

3. The cultural relics identification and explanation system based on generative artificial intelligence according to claim 2 is characterized by: The first platform (51) is equipped with a position indicating light source (55), the position indicating light source (55) is installed at the position of the visual sensor (52), and the position indicating light source (55) indicates the current scanning position of the visual sensor (52) through a light spot.

4. The cultural relics identification and explanation system based on generative artificial intelligence according to claim 3 is characterized by: It also includes a keyword recognition module (31), wherein the conversion module (3) receives information from the sound input module (21) and then inputs the information into the keyword recognition module (31), and the keyword recognition module (31) recognizes the keyword and activates the visual sensor (52).

5. The cultural relics identification and explanation system based on generative artificial intelligence according to claim 2 is characterized by: The first platform (51) is a glasses frame, and the visual sensor (52), the sound collecting component (53), and the playing component (54) are detachably mounted on the first platform (51).

6. The cultural relics identification and explanation system based on generative artificial intelligence according to claim 5 is characterized by: The visual sensor (52), the sound collecting component (53), and the playing component (54) are fixedly connected to the same mounting plate (511), the mounting plate (511) is fixedly mounted with a C-shaped clamp (512), and the C-shaped clamp (512) is mounted on the first platform (51).

7. The cultural relics identification and explanation system based on generative artificial intelligence according to claim 3 is characterized by: The conversion module (3) is connected to an identification database (11), and the identification database (11) stores information on the sensitivity of cultural relics to light sources. The identification module (1) is signal-connected to the position-indicating light source (55).

8. A system for identifying and explaining cultural relics based on generative artificial intelligence according to any one of claims 2 to 7, characterized in that: The sound collecting component (53) is a bone conduction sound collecting component.

Images