AI voice interaction method and system for smart office

Abstract

The invention discloses an AI voice interaction method and system for smart office, and belongs to the technical field of smart office, and the method comprises the steps: obtaining the voice information of a worker in an office area, converting the voice information into statement information, and dividing the statement information into a plurality of statements; preliminarily analyzing a first semantic intention of the voice information based on the multiple segments of statements obtained through division; face information of workers in the office area is obtained, the face information is compared with the face database, and identity information of the workers is judged; based on the identity information of the worker, combining the first semantic intention, and performing secondary analysis to obtain a second semantic intention of the voice information; based on the second semantic intention of the voice information, determining an operation instruction of the worker, and calling a function module to operate according to the operation instruction; and feeding back an operation result of the operation instruction, and defining the instruction which is not successfully operated as a to-do list. According to the invention, the problem of inaccurate semantic recognition caused by complex statements is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of smart office, and in particular to an AI voice interaction method and system for smart office. Background Art

[0002] With the rapid development of science and technology, artificial intelligence has penetrated into every aspect of our lives. Among them, intelligent voice interaction, as an important branch of AI technology, is changing the way we communicate at an unprecedented speed. From smart home control to office automation applications, to the convenience of daily communication, intelligent voice interaction is redefining our connection with the world.

[0003] Intelligent voice interaction technology mainly includes three core parts: voice recognition, natural language processing and voice synthesis. Voice recognition technology converts the user's voice into text information, natural language processing technology understands and processes the text information, and finally voice synthesis technology feeds back the processing results to the user in the form of voice. This process realizes a closed-loop interaction from voice to text and then to voice.

[0004] The intelligent voice interaction technology in the existing technology has the following problems in the office environment: 1. Single function: It mainly focuses on basic functions such as voice recognition and voice synthesis, and lacks deep integration and intelligent interaction capabilities with office software and hardware platforms; 2. Poor interactive experience: The accuracy of voice command recognition is low, the semantic understanding ability is insufficient, and it is difficult to meet complex office needs; 3. Lack of personalization: It cannot be customized according to user habits and needs, and the user experience is poor; 4. Insufficient integration of AI capabilities: There is a lack of integration and utilization of the company's existing AI capabilities, making it difficult to realize the potential of AI.

[0005] Therefore, how to provide a voice interaction method that can solve the problems existing in the prior art is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0006] To this end, the present invention provides an AI voice interaction method and system for smart office to solve the problems in the prior art.

[0007] In order to achieve the above object, the present invention provides the following technical solutions:

[0008] According to a first aspect of the present invention, there is provided an AI voice interaction method for smart office, comprising:

[0009] Step S1: Acquire voice information of staff in the office area, convert the voice information into sentence information, and divide the sentence information into multiple sentences;

[0010] Step S2: Preliminarily analyzing the first semantic intention of the speech information based on the divided multiple sentences;

[0011] Step S3: Obtaining facial information of staff members in the office area, comparing it with the facial database, and determining the identity information of the staff members;

[0012] Step S4: Based on the identity information of the staff member and in combination with the first semantic intent, a second semantic intent of the voice information is obtained by secondary analysis;

[0013] Step S5: determining the staff member's operation instruction based on the second semantic intention of the voice information, and calling the function module to perform operation according to the operation instruction;

[0014] Step S6: Feedback the operation result of the operation instruction, and define the instructions that have not been successfully operated as to-do items.

[0015] Furthermore, in step S1, voice information of staff in the office area is obtained, the voice information is converted into sentence information, and the sentence information is divided into multiple sentences, specifically:

[0016] Based on the sentence information obtained by the transformation, the pause time in the sentence information is obtained;

[0017] Divide the sentence information into sentence segments according to the pause time between the sentence information to obtain n sentence segments;

[0018] Analyze the starting and ending characters of n sentences, and analyze the coherence relationship between the ending characters of the previous sentence and the starting characters of the next sentence;

[0019] Based on the coherent relationship between the last character of the previous paragraph and the starting character of the next paragraph, the sentence information is re-divided into sentence paragraphs to obtain m sentence paragraphs.

[0020] Furthermore, in step S2, based on the divided multiple sentences, the first semantic intention of the voice information is preliminarily analyzed, specifically:

[0021] Based on the acquired multiple sentences, keywords in different sentences are extracted, and the multiple sentences are classified according to the keywords in different sentences;

[0022] Based on the statement being a primary authority, it is defined as a first-level statement, calling a first functional module corresponding to the first-level statement, and causing the first functional module to respond;

[0023] Based on the statement being of intermediate authority, it is defined as a second-level statement, calling a second functional module corresponding to the second-level statement, and causing the second functional module to wait for a response;

[0024] Based on the fact that the statement is a high-level permission, it is defined as a third-level statement, and the third functional module corresponding to the third-level statement is called, so that the third functional module waits for a response.

[0025] Furthermore, in step S4, based on the identity information of the staff member and in combination with the first semantic intent, a second semantic intent of the voice information is obtained through secondary analysis, specifically:

[0026] Based on the identity information of the staff member, obtaining the authority level of the staff member;

[0027] Based on the staff member's primary authority, only the first functional module responds to the operation instruction of the first level statement;

[0028] Based on the staff's authority being intermediate authority, the second functional module is made to respond to the operation instruction of the second level statement on the basis of the first functional module responding to the operation instruction of the first level statement;

[0029] Based on the fact that the staff member has high-level authority, the first function module, the second function module and the third function module simultaneously respond to the operation instructions of the first semantic intention, the second semantic intention and the third semantic intention.

[0030] Furthermore, the multiple sentences are graded according to the keywords in different sentences, specifically: the keywords in different sentences are classified, and the multiple sentences are graded according to the authority levels of the keywords.

[0031] Furthermore, the permission level of the keyword is determined according to the device permission level corresponding to the keyword.

[0032] Furthermore, based on the identity information of the staff member, the authority level of the staff member is obtained, specifically:

[0033] If the staff member's position is a grassroots position, the staff member's authority is defined as primary authority;

[0034] If the staff member's position is a mid-level position, define the staff member's authority as mid-level authority;

[0035] If the staff member's position is a senior position, define the staff member's permissions as senior permissions.

[0036] Furthermore, the secondary analysis to obtain the second semantic intention of the voice information further includes:

[0037] Based on the staff member's high-level authority, obtain the keywords of the previous sentence;

[0038] Predict the keywords of the next sentence based on the keywords of the previous sentence;

[0039] Based on the predicted keywords of the next sentence, the corresponding device is called to wait for a response;

[0040] Obtain the keywords of the actual next sentence, and determine whether the keywords of the actual next sentence are similar to the keywords of the predicted next sentence;

[0041] If the keywords of the actual next sentence are similar to the keywords of the predicted next sentence, the device waiting for response responds immediately;

[0042] If the actual keyword of the next sentence is not similar to the predicted keyword of the next sentence, the waiting response state of the device is released.

[0043] According to a second aspect of the present invention, there is provided an AI voice interaction system for smart office, comprising:

[0044] An information acquisition unit, used to acquire voice information of staff in the office area, convert the voice information into sentence information, and divide the sentence information into multiple sentences;

[0045] A first analysis unit, used for dividing the obtained multiple sentences and preliminarily analyzing the first semantic intention of the speech information;

[0046] A judgment unit, used to obtain the face information of the staff in the office area, compare it with the face database, and judge the identity information of the staff;

[0047] A second analysis unit is used to perform a secondary analysis based on the identity information of the staff member and the first semantic intent to obtain a second semantic intent of the voice information;

[0048] An instruction operation unit, used to determine the operation instruction of the staff member based on the second semantic intention of the voice information, and call the function module to operate according to the operation instruction;

[0049] The feedback unit is used to feed back the operation result of the operation instruction, and define the instructions that have not been successfully operated as to-do items.

[0050] The present invention has the following advantages:

[0051] The present invention obtains voice information of staff in an office area, converts the voice information into sentence information, and divides the sentence information into multiple sentences; based on the divided multiple sentences, preliminarily analyzes the first semantic intention of the voice information; obtains face information of the staff in the office area, compares it with a face database, and determines the identity information of the staff; based on the identity information of the staff and in combination with the first semantic intention, a second semantic intention of the voice information is obtained through secondary analysis; based on the second semantic intention of the voice information, the operation instructions of the staff are determined, and a function module is called to perform operations according to the operation instructions; the operation results of the operation instructions are fed back, and the instructions that have not been successfully operated are defined as to-do items.

[0052] The present invention converts the voice information of the staff into sentence information, and segments the sentence information, analyzes the intention of the sentence segment by segment, strengthens the voice recognition processing capability of the intelligent AI, and avoids the problem of inaccurate semantic recognition caused by complex sentences. The present invention also identifies the staff's face information, thereby identifying their identity information, and determines the authority level based on the identity information, thereby personalizing the staff's user habits and needs and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0054] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0055] Figure 1 A flowchart of an AI voice interaction method for smart office provided by the present invention;

[0056] Figure 2 A connection block diagram of an AI voice interaction system for smart office provided by the present invention. DETAILED DESCRIPTION

[0057] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are 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.

[0058] According to a first aspect of the present invention, an AI voice interaction method for smart office is provided, such as Figure 1 As shown, including:

[0059] Step S1: Acquire voice information of staff in the office area, convert the voice information into sentence information, and divide the sentence information into multiple sentences;

[0060] Step S2: Preliminarily analyzing the first semantic intention of the speech information based on the divided multiple sentences;

[0061] Step S3: Obtain the facial information of the staff in the office area, compare it with the facial database, and determine the identity information of the staff;

[0062] Step S4: Based on the identity information of the staff member and in combination with the first semantic intent, a second semantic intent of the voice information is obtained by secondary analysis;

[0063] Step S5: Based on the second semantic intention of the voice information, determine the staff's operation instruction, and call the function module to operate according to the operation instruction;

[0064] Step S6: Feedback the operation result of the operation instruction, and define the instructions that have not been successfully operated as to-do items.

[0065] The present invention converts the voice information of the staff into sentence information, and segments the sentence information, analyzes the intention of the sentence segment by segment, strengthens the voice recognition processing capability of the intelligent AI, and avoids the problem of inaccurate semantic recognition caused by complex sentences. The present invention also identifies the staff's face information, thereby identifying their identity information, and determines the authority level based on the identity information, thereby personalizing the staff's user habits and needs and improving the user experience.

[0066] In step S1, voice information of staff in the office area is obtained, the voice information is converted into sentence information, and the sentence information is divided into multiple sentences, specifically:

[0067] Based on the sentence information obtained by the transformation, the pause time in the sentence information is obtained;

[0068] According to the pause time between the sentence information, the sentence information is divided into sentence paragraphs to obtain n sentence paragraphs;

[0069] Analyze the starting and ending characters of n sentences, and analyze the coherence relationship between the ending characters of the previous sentence and the starting characters of the next sentence;

[0070] Based on the coherence relationship between the last character of the previous paragraph and the starting character of the next paragraph, the sentence information is re-divided into sentence paragraphs to obtain m sentences.

[0071] Generally speaking, if there is a pause in a speech, it means that the previous operation instruction has been fully expressed. According to the pause time between the sentence information, the sentence information is divided into sentence segments, and n sentences are obtained. According to the n sentences, n operation instructions are implemented. However, if the speech is interrupted, the intelligent AI cannot recognize it completely, and the operation instruction cannot be implemented. It needs to be re-sent, wasting the working time of the staff.

[0072] In order to improve the ability of semantic understanding, the present invention can establish a vocabulary, and judge the coherence relationship between characters by identifying whether each character often appears together. If the connection frequency between characters is greater than the preset frequency, it is determined that there is a coherence relationship between the two characters, otherwise, there is no coherence relationship. If there is a coherence relationship between the last character of the previous paragraph and the starting character of the next paragraph, it means that there is a problem with the sentence segmentation, so the previous sentence and the next sentence are spliced ​​together, and the paragraphs between the sentences are re-divided to obtain m sentences, where m is less than n, which can avoid the problem of inaccurate semantic recognition caused by complex sentences.

[0073] In step S2, based on the divided multiple sentences, the first semantic intention of the voice information is preliminarily analyzed, specifically:

[0074] Based on the acquired multiple sentences, keywords in different sentences are extracted, and the multiple sentences are classified according to the keywords in different sentences;

[0075] Based on the statement being a primary authority, it is defined as a first-level statement, and the first functional module corresponding to the first-level statement is called to make the first functional module respond;

[0076] Based on the statement being of intermediate authority, it is defined as a second-level statement, and the second functional module corresponding to the second-level statement is called, so that the second functional module waits for a response;

[0077] Based on the statement being a high-level permission, it is defined as a third-level statement, and the third functional module corresponding to the third-level statement is called, so that the third functional module waits for a response.

[0078] According to the keywords in different sentences, multiple sentences are graded. Specifically, the keywords in different sentences are classified, and the multiple sentences are graded according to the permission level of the keywords. The permission level of the keyword is determined according to the device permission level corresponding to the keyword. For example, the keywords in the sentence "Can you help me open the whiteboard?" are "open" and "whiteboard". "Open" is an action keyword that can be recognized by existing AI. According to the device keywords such as "whiteboard", the permission level of the sentence is determined. "Whiteboard" is a device that can be operated by all staff members, and it only needs to have primary permissions, so the sentence is defined as a first-level sentence. Determine the level of the sentence according to the device permissions corresponding to the device keywords in the sentence.

[0079] If the device is identified as a public device, the operator can respond to the operation instruction before identifying the staff member. However, if the device is identified as a non-public device, further semantic recognition is required based on the staff member's identity information.

[0080] In step S4, based on the identity information of the staff member and in combination with the first semantic intent, a second semantic intent of the voice information is obtained through secondary analysis, specifically:

[0081] Based on the staff's identity information, obtain the staff's authority level;

[0082] Based on the staff's primary authority, only the first functional module responds to the operation instructions of the first level statement;

[0083] Based on the staff's authority being at the intermediate level, the second functional module is made to respond to the operation instruction of the second level statement on the basis that the first functional module responds to the operation instruction of the first level statement;

[0084] Based on the staff's high-level authority, the first function module, the second function module and the third function module simultaneously respond to the operation instructions of the first semantic intention, the second semantic intention and the third semantic intention.

[0085] Based on the staff's identity information, the staff's authority level is obtained, specifically:

[0086] If the staff member's position is a grassroots position, the staff member's authority is defined as primary authority;

[0087] If the staff member's position is a mid-level position, define the staff member's authority as mid-level authority;

[0088] If the staff member's position is a senior position, define the staff member's permissions as senior permissions.

[0089] The staff member's operating authority is determined according to his or her position. When the staff member has primary-level authority, the equipment he or she can respond to instructions is public equipment; when the staff member has intermediate-level authority, the equipment he or she can respond to instructions is public equipment and equipment dedicated to middle-level leaders; when the staff member has senior-level authority, the equipment he or she can respond to instructions is public equipment, equipment dedicated to middle-level leaders, and equipment dedicated to senior leaders.

[0090] By recognizing the staff's facial information, we can identify their identity information and determine the authority level based on the identity information, so as to personalize the staff's user habits and needs and improve the user experience.

[0091] The secondary analysis obtains the second semantic intention of the speech information, which also includes:

[0092] Based on the staff's advanced permissions, obtain the keywords of the previous sentence;

[0093] Predict the keywords of the next sentence based on the keywords of the previous sentence;

[0094] Based on the predicted keywords of the next sentence, the corresponding device is called to wait for a response;

[0095] Obtain the keywords of the actual next sentence, and determine whether the keywords of the actual next sentence are similar to the keywords of the predicted next sentence;

[0096] If the keywords of the actual next sentence are similar to the keywords of the predicted next sentence, the device waiting for response responds immediately;

[0097] If the actual keyword of the next sentence is not similar to the predicted keyword of the next sentence, the waiting response state of the device is released.

[0098] For example, when entering an office in winter, you usually need to close the window after turning on the air conditioner. "Turn on the air conditioner" and "close the window" are linked. According to "turn on the air conditioner", it can be predicted that the next sentence should be "close the window". After the air conditioner responds to the operation instruction, the window is put in a waiting state. Determine whether the keywords of the actual next sentence are similar to the keywords of the predicted next sentence. If the action keyword "close" and the device keyword "window" are similar, the window will immediately respond to the operation and close. If the action keyword "close" and the device keyword "window" are not similar, the window's waiting state is released.

[0099] According to a second aspect of the present invention, an AI voice interaction system for smart office is provided, such as Figure 2 As shown, including:

[0100] An information acquisition unit, used to acquire voice information of staff in the office area, convert the voice information into sentence information, and divide the sentence information into multiple sentences;

[0101] A first analysis unit is used to divide the obtained multiple sentences and preliminarily analyze the first semantic intention of the speech information;

[0102] A judgment unit is used to obtain the facial information of the staff in the office area, compare it with the facial database, and judge the identity information of the staff;

[0103] The second analysis unit is used to perform a secondary analysis based on the identity information of the staff member and the first semantic intention to obtain a second semantic intention of the voice information;

[0104] An instruction operation unit, used to determine the operation instruction of the staff based on the second semantic intention of the voice information, and call the function module to operate according to the operation instruction;

[0105] The feedback unit is used to feedback the operation results of the operation instructions and define the instructions that have not been successfully operated as to-do items.

[0106] The voice information of the staff in the office area is obtained through the information acquisition unit, the voice information is converted into sentence information, and the sentence information is divided into multiple sentences; based on the multiple sentences obtained by the division, the first analysis unit preliminarily analyzes the first semantic intention of the voice information; the face information of the staff in the office area is obtained, and the judgment unit judges the identity information of the staff by comparing with the face database; the instruction operation unit performs a secondary analysis on the second semantic intention of the voice information based on the identity information of the staff and the first semantic intention; based on the second semantic intention of the voice information, the operation instruction of the staff is determined, and the function module is called to operate according to the operation instruction; the feedback unit feeds back the operation result of the operation instruction, and defines the instruction that has not been successfully operated as a to-do item.

[0107] The present invention converts the voice information of the staff into sentence information, and segments the sentence information, analyzes the intention of the sentence segment by segment, strengthens the voice recognition processing capability of the intelligent AI, and avoids the problem of inaccurate semantic recognition caused by complex sentences. The present invention also identifies the staff's face information, thereby identifying their identity information, and determines the authority level based on the identity information, thereby personalizing the staff's user habits and needs and improving the user experience.

[0108] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. An AI voice interaction method for smart office, characterized in that: include: Step S1: Acquire voice information of staff in the office area, convert the voice information into sentence information, and divide the sentence information into multiple sentences; Step S2: Preliminarily analyzing the first semantic intention of the speech information based on the divided multiple sentences; Step S3: Obtaining facial information of staff members in the office area, comparing it with the facial database, and determining the identity information of the staff members; Step S4: Based on the identity information of the staff member and in combination with the first semantic intent, a second semantic intent of the voice information is obtained by secondary analysis; Step S5: determining the staff member's operation instruction based on the second semantic intention of the voice information, and calling the function module to perform operation according to the operation instruction; Step S6: Feedback the operation result of the operation instruction, and define the instructions that have not been successfully operated as to-do items.

2. The AI ​​voice interaction method for smart office according to claim 1, characterized in that: In step S1, voice information of staff in the office area is obtained, the voice information is converted into sentence information, and the sentence information is divided into multiple sentences, specifically: Based on the sentence information obtained by the transformation, the pause time in the sentence information is obtained; Divide the sentence information into sentence segments according to the pause time between the sentence information to obtain n sentence segments; Analyze the starting and ending characters of n sentences, and analyze the coherence relationship between the ending characters of the previous sentence and the starting characters of the next sentence; Based on the coherent relationship between the last character of the previous paragraph and the starting character of the next paragraph, the sentence information is re-divided into sentence paragraphs to obtain m sentence paragraphs.

3. The AI ​​voice interaction method for smart office according to claim 1, characterized in that: In step S2, based on the divided multiple sentences, the first semantic intention of the voice information is preliminarily analyzed, specifically: Based on the acquired multiple sentences, keywords in different sentences are extracted, and the multiple sentences are classified according to the keywords in different sentences; Based on the statement being a primary authority, it is defined as a first-level statement, calling a first functional module corresponding to the first-level statement, and causing the first functional module to respond; Based on the statement being of intermediate authority, it is defined as a second-level statement, calling a second functional module corresponding to the second-level statement, and causing the second functional module to wait for a response; Based on the fact that the statement is a high-level permission, it is defined as a third-level statement, and the third functional module corresponding to the third-level statement is called, so that the third functional module waits for a response.

4. The AI ​​voice interaction method for smart office according to claim 3, characterized in that: In step S4, based on the identity information of the staff member and in combination with the first semantic intent, a second semantic intent of the voice information is obtained through secondary analysis, specifically: Based on the identity information of the staff member, obtaining the authority level of the staff member; Based on the staff member's primary authority, only the first functional module responds to the operation instruction of the first level statement; Based on the staff's authority being intermediate authority, the second functional module is made to respond to the operation instruction of the second level statement on the basis of the first functional module responding to the operation instruction of the first level statement; Based on the fact that the staff member has high-level authority, the first function module, the second function module and the third function module simultaneously respond to the operation instructions of the first semantic intention, the second semantic intention and the third semantic intention.

5. The AI ​​voice interaction method for smart office according to claim 3, characterized in that: The method of grading the multiple sentences according to the keywords in different sentences specifically includes: classifying the keywords in different sentences, and grading the permissions of the multiple sentences according to the permission levels of the keywords.

6. The AI ​​voice interaction method for smart office according to claim 5, characterized in that: Determine the permission level of the keyword based on the device permission level corresponding to the keyword.

7. The AI ​​voice interaction method for smart office according to claim 4, characterized in that: The authority level of the staff member is obtained based on the identity information of the staff member, specifically: If the staff member's position is a grassroots position, the staff member's authority is defined as primary authority; If the staff member's position is a mid-level position, define the staff member's authority as mid-level authority; If the staff member's position is a senior position, define the staff member's permissions as senior permissions.

8. The AI ​​voice interaction method for smart office according to claim 4, characterized in that: The second semantic intention of the voice information obtained by the secondary analysis also includes: Based on the staff member's high-level authority, obtain the keywords of the previous sentence; Predict the keywords of the next sentence based on the keywords of the previous sentence; Based on the predicted keywords of the next sentence, the corresponding device is called to wait for a response; Obtain the keywords of the actual next sentence, and determine whether the keywords of the actual next sentence are similar to the keywords of the predicted next sentence; If the keywords of the actual next sentence are similar to the keywords of the predicted next sentence, the device waiting for response responds immediately; If the actual keyword of the next sentence is not similar to the predicted keyword of the next sentence, the waiting response state of the device is released.

9. An AI voice interaction system for smart office, used to implement the AI ​​voice interaction method for smart office as described in any one of claims 1 to 8, characterized in that: include: An information acquisition unit, used to acquire voice information of staff in the office area, convert the voice information into sentence information, and divide the sentence information into multiple sentences; A first analysis unit, used for dividing the obtained multiple sentences and preliminarily analyzing the first semantic intention of the speech information; A judgment unit, used to obtain face information of staff members in the office area, compare it with the face database, and judge the identity information of the staff members; A second analysis unit is used for performing a secondary analysis based on the identity information of the staff member and the first semantic intent to obtain a second semantic intent of the voice information; An instruction operation unit, used to determine the operation instruction of the staff member based on the second semantic intention of the voice information, and call the function module to operate according to the operation instruction; The feedback unit is used to feed back the operation result of the operation instruction, and define the instructions that have not been successfully operated as to-do items.

Images