WO2020006863A1 - Automatic approval comment input method and apparatus, computer device, and storage medium - Google Patents

Abstract

An automatic approval comment input method and apparatus, a computer device, and a storage medium, used to solve the issue in which approval work occupies a lot of working time and the approval process is inefficient. The method comprises: upon detecting that a front end window of a target terminal is an approval window for a work event, acquiring a facial image of processing personnel in front of a display screen of the target terminal (S101); using an expression recognition technique to analyze the facial image, and acquiring an expression value of the processing personnel in front of the display screen (S102), the expression value representing an approval attitude of the processing personnel in front of the display screen with respect to the work event; determining, according to an expression and comment correspondence, an approval comment corresponding to the expression value of the processing personnel in front of the display screen (S103), the expression and comment correspondence comprising a correspondence between the expression value and the approval comment; and inputting the approval comment into the approval window (S104).

Description

Method, device, computer equipment and storage medium for automatically inputting approval opinions

This application is based on a Chinese invention patent application filed on July 06, 2018 with application number 201810735894.7, entitled "Method, Device, Computer Equipment, and Storage Medium for Automatic Input of Approval Opinions", and claims its priority.

Technical field

The present application relates to the field of intelligence, and in particular, to a method, a device, a computer device, and a storage medium for automatically inputting approval opinions.

Background technique

In the content of corporate office, approval work should be one of the most common and content-intensive tasks. At present, a user needs to manually input approval opinions when conducting approval. When there are many approval tasks, it is likely to occupy a lot of work time of the user. Therefore, it is necessary to find an efficient way to complete the approval work.

Summary of the invention

Based on this, it is necessary to provide a method, a device, a computer device, and a storage medium for automatically inputting an approval opinion in order to improve the efficiency of the approval work in response to the above technical problems.

A method for automatically entering approval opinions, including:

When it is detected that the front window of the target terminal is an approval window for a work event, collecting a face image of a processing person in front of the display of the target terminal;

Use facial expression recognition technology to analyze the face image to obtain facial expression values of the front processing person, the facial expression values reflecting the front processing person's approval attitude towards the work event;

Determining an approval opinion corresponding to the expression value of the front processor according to the corresponding relationship of the expression opinion, and the corresponding relationship of the expression opinion records the corresponding relationship between the expression value and the approval opinion;

The approval opinions are input into the approval window.

A device for automatically inputting approval opinions includes:

A face image acquisition module, configured to collect a face image of a person in front of a display screen of the target terminal when it is detected that the front window of the target terminal is an approval window for a work event;

An expression value analysis module, configured to analyze the face image by using expression recognition technology to obtain an expression value of the front processor, the expression value reflects the approval attitude of the front processor to the work event;

The approval opinion determination module is configured to determine an approval opinion corresponding to the expression value of the front processor according to the corresponding relationship of the expression opinion, where the corresponding relationship of the expression opinion records the corresponding relationship between the expression value and the approval opinion;

An opinion input module is configured to input the approval opinions into the approval window.

A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, and the processor implements the computer-readable instructions to implement the above-mentioned automatic input of approval opinions Steps of the method.

One or more non-volatile readable storage media storing computer readable instructions, the computer readable storage medium storing computer readable instructions, so that the one or more processors execute the above-mentioned automatic input approval opinion Method steps.

Details of one or more embodiments of the present application are set forth in the accompanying drawings and description below, and other features and advantages of the present application will become apparent from the description, the drawings, and the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to explain the technical solutions of the embodiments of the present application more clearly, the drawings used in the description of the embodiments of the application will be briefly introduced below. Obviously, the drawings in the following description are just some embodiments of the application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without paying creative labor.

FIG. 1 is a schematic diagram of an application environment of a method for automatically inputting approval opinions in an embodiment of the present application; FIG.

2 is a flowchart of a method for automatically inputting an approval opinion in an embodiment of the present application;

3 is a schematic flowchart of an application scenario in step S102 of a method for automatically inputting an approval opinion in an embodiment of the present application;

4 is a schematic flowchart of an application scenario in step S103 of a method for automatically inputting an approval opinion in an embodiment of the present application;

5 is a schematic flowchart of a method for automatically inputting an approval opinion in an embodiment of the present application in an application scenario to determine an expression value interval in advance;

6 is a schematic flowchart of a method for automatically determining an approval opinion in an application scenario according to an embodiment of the present application;

FIG. 7 is a schematic flowchart of determining an attitude value according to a head movement in an application scenario of a method for automatically inputting an approval opinion in an embodiment of the present application; FIG.

8 is a schematic structural diagram of an apparatus for automatically inputting an approval opinion in an embodiment of the present application;

FIG. 9 is a schematic diagram of a computer device in an embodiment of the present application.

detailed description

In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

The method for automatically inputting approval opinions provided in this application can be applied in the application environment shown in FIG. 1, in which a client communicates with a server through a network. Among them, the client may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple servers.

In one embodiment, as shown in FIG. 2, a method for automatically inputting an approval opinion is provided. The method is applied to the server in FIG. 1 as an example, and includes the following steps:

S101. When it is detected that the front-end window of the target terminal is an approval window for a work event, collect a face image of a person processing in front of the display screen of the target terminal;

In this embodiment, a camera may be set on the target terminal in advance, and the camera may shoot toward the front of the display screen. When the processor uses the target terminal to approve a work event, the approval window of the target terminal is opened, and the approval window at this time belongs to the front-end window of the target terminal. The execution subject (server) can consider that the current user is performing approval work, so The camera collects a face image of the processing person.

S102. Analyze the face image by using an expression recognition technology to obtain an expression value of the front processing person, where the expression value reflects the approval attitude of the front processing person to the work event;

It can be understood that, in this embodiment, a face image of a processing person is collected, and the purpose of this embodiment is to obtain the attitude of the processing person to the currently approved work event by analyzing the face image. Generally speaking, when a handler approves a work event, if the handler has a consenting attitude, the handler's psychological emotions should be relaxed and pleasant, and the relaxed expression reflected on his face (for example, his eyebrows are loosened) On the other hand, if the person handling the objection is opposed, the person's psychological emotions should be tangled and disgusting, and reflected on his face as a tense expression (such as frowning). It can be seen that by analyzing and processing the human facial expressions, it is possible to accurately determine the processing person's approval attitude for a certain work event.

It should be noted that there are many existing facial expression recognition technologies, and specific facial expression recognition technologies are not limited here, but basically all facial expression recognition technologies will quantify and process human facial expressions after analyzing facial images, and use facial expressions Value representation. In this embodiment, the higher the expression value, the better the psychological emotion of the processor, reflecting the approval attitude of the processor on the work event. On the contrary, the lower the expression value, the more the psychological emotion of the processor Poor, reflecting that the processor's approval attitude towards the work incident is opposed.

Further, as shown in FIG. 3, the step S102 may specifically include:

S201. Extract each action unit of a micro-expression from the face image;

S202. Obtain an expression value corresponding to each of the action units according to a preset micro-expression score standard.

S203: Calculate and obtain the current expression value of the front-processing person according to the expression value corresponding to each of the action units.

For step S201, the types of action units in this embodiment mainly include 19 types of internationally common action units (AU) in Table 1 below:

Table 1 19 types of AU

AU number	AU description
AU1	Raised inner eyebrow
AU2	Raised eyebrows
AU4	Eyebrow down
AU5	Eyes up
AU6	Cheek raised
AU7	Eyelid tightening
AU9	Wrinkled nose
AU10	Upper lip up
AU12	Mouth raised
AU14	Tighten your mouth
AU15	Corner of mouth
AU16	Lower lip press
AU17	Jaw tightening
AU18	Folds of lips
AU20	Lips stretch
AU23	Lips shrink
AU24	Tight lips
AU25	Separate upper and lower lips
AU26	Jaw drop

It can be understood that after collecting and obtaining a face image of a processing person, one, two, or more action units (AU) of the above 19 types can be extracted therefrom. It can be known that the action unit corresponds to the current facial features and actions of the processor, and these action units together reflect the current mood or emotion of the processor. For example, when people are happy, their facial movements include: the corners of the mouth are raised, the cheeks are raised, and the eyelids are tightened, that is, the above-mentioned AU12, AU6, and AU7.

For step S202, in this embodiment, the server may preset the expression values corresponding to 19 types of AUs and record them as micro-expression score standards. For example, in a specific application scenario, the micro-expression score standards are shown in Table 2 below:

Table 2 19 types of AU

AU number	AU description	Expression value
AU1	Raised inner eyebrow	2
AU2	Raised eyebrows	1
AU4	Eyebrow down	1
AU5	Eyes up	3
AU6	Cheek raised	1
AU7	Eyelid tightening	4
AU9	Wrinkled nose	2
AU10	Upper lip up	3
AU12	Mouth raised	3
AU14	Tighten your mouth	1
AU15	Corner of mouth	-1
AU16	Lower lip press	1
AU17	Jaw tightening	2
AU18	Folds of lips	3
AU20	Lips stretch	2
AU23	Lips shrink	1
AU24	Tight lips	1
AU25	Separate upper and lower lips	2
AU26	Jaw drop	4

It can be seen that by using the micro-expression scale, after extracting each action unit AU in the face image, the micro-expression scale can be queried to obtain the expression value corresponding to each action unit. In the above specific application scenario, a larger expression value indicates that the action unit responds better to a person's mood.

For step S203, after obtaining the expression value corresponding to each of the action units, the sum of these expression values may be calculated as the current expression value of the processor. For example, following the above example, if the processor's action units are AU12, AU6, and AU7, the corresponding facial expression values obtained are 3, 1, and 4, respectively, so that the current facial expression value of the processor is 8.

S103. Determine an approval opinion corresponding to the facial expression value of the person in front of the processing according to the corresponding relationship of the facial expression opinion, where the facial expression correspondence records the correspondence between the facial expression value and the approval opinion;

In this embodiment, the server may preset a plurality of approval opinions, and these approval opinions correspond to different expression values, respectively, and establish the corresponding relationship of the expression opinions. After the expression value of the person in front of the processing is determined, an approval opinion corresponding to the expression value may be determined according to the corresponding relationship of the expression opinion. For example, the server may preset three approval opinions of "agree", "disapprove" and "oppose", and these three approval opinions correspond to three different expression value intervals. In this embodiment, the higher the expression value, the more the processor agrees with the approved work event. Therefore, the above three approval opinions also correspond to the three high-to-low expression value intervals, for example, it can be [70,100], [40,70], [0,40].

Further, as shown in FIG. 4, step S103 may include:

S301. Determine an expression value interval in which the expression value of the person in front of the processing falls, among the preset expression value intervals, and each expression value interval is preset and corresponds to each preset approval opinion;

S302. Obtain an approval opinion corresponding to the determined expression value interval.

For the above steps S301 and S302, it can be understood that, as mentioned above, these expression value intervals can be set in advance by the server, and each expression value interval corresponds to an approval opinion respectively. Step S301 first determines which expression value the processor falls into In the expression value interval, and then obtain the approval opinion corresponding to the determined expression value interval through step S302, it can be considered that the acquired approval opinion is the processor's approval opinion on the work event.

Further, considering that each expression value interval is manually set by the administrator of the server, although this setting method is more free and flexible, it is difficult to achieve accuracy and may even cause human misjudgment. Therefore, in order to improve the accuracy of each expression value interval and make the setting of each expression value interval more in line with the actual application situation, as shown in FIG. 5, each expression value interval can be determined in advance through the following steps:

S401: Obtain each historical approval opinion and the facial expression value corresponding to each historical approval opinion when the front processor's historical approval work event occurs;

S402. Classify each of the historical approval opinions according to the approval attitude corresponding to the content of the historical approval opinions to obtain each opinion category;

S403. Determine each expression value interval corresponding to each of the opinion types one by one, and the boundary value of the expression value interval is determined by the expression value corresponding to the historical approval opinion in the opinion category corresponding to the expression value interval.

For step S401, it can be understood that the server may collect and obtain each historical approval opinion and the expression value corresponding to each historical approval opinion of the front processor during the historical approval work event. It can be known that these historical approval opinions are opinions input by the processor himself. When collecting historical approval opinions, he also obtained the expression value of the processor himself, so the correspondence between the historical approval opinions and expression values is accurate. It accurately reflects the specific performance of the handler when approving work incidents. Generally speaking, different processors have different attitudes toward the same work event. Even with the same attitude, the expressions of different processors will have slight deviations. For example, two processors agree on the same approved work event, but one processor may nod and smile, while the other processor simply smiles. It can be known from this that the expression value interval determined for a certain processor may not be applicable to another processor, so it is best to calculate and determine each expression value interval used individually for each processor.

For step S402, it can be understood that after obtaining the historical approval opinions, the historical approval opinions can be classified according to the approval attitude corresponding to the content of the historical approval opinions, for example, it can be divided into "agree", "not" "Approve" and "oppose" the three categories, of course, can also be subdivided into more categories, not limited here.

For step S403, after determining each opinion category, for an opinion category, the expression value corresponding to the historical approval opinion that the processor belongs to the opinion category can be obtained, and then the maximum and minimum values are taken from these expression values. Thus, the boundary value of the expression value interval corresponding to the opinion category is determined. For example, there are 100 historical approval opinions in the "Agree" category. The expression values corresponding to the 100 historical approval opinions are: 72, 75, 86, ..., 99, 71, 100, 95, and the maximum value is 100. The minimum value is 70, so it can be determined that the range of expression values corresponding to the "Agree" category is [70,100]. It can be understood that the larger the amount of data of historical approval opinions, the more accurate the boundary value of the determined expression value interval.

Further, as shown in FIG. 6, before step S103, the method for automatically inputting an approval opinion provided in this embodiment may further include:

S501. Obtain each historical facial expression value collected during the historical approval work event of the front processor;

S502. Select a historical expression value that is closest to the expression value of the person in front of the processing from the historical expression values.

S503. Determine whether the error between the selected historical expression value and the expression value of the person in front of the processing is within a preset range, if yes, execute step S504, and if not, execute step S103;

S504. Determine the historical approval opinion corresponding to the selected historical expression value as the approval opinion for the work event.

With regard to the above steps S501 to S504, it can be understood that the steps S301 and S302 estimate the approval opinion of the processor through the interval in which the expression value falls, but there is a certain error in the determination method using the interval. In this embodiment, through the above steps S501 to S504, before the interval determination, first find whether the expression value of the processor is close to a historical expression value (including the same case) when the historical approval work event of the processor is performed. , It can be determined that the current approval opinion of the processor is the same as the historical approval opinion corresponding to that historical expression value; if not, then the interval judgment method is used. It can be seen that this processing method is more accurate than the method using all interval judgments.

For step S501, the principle is similar to the above step 401, and details are not described herein again.

For step S502, after obtaining the facial expression value of the processor in front, first select a historical facial expression value closest to the historical facial expression value of the processor. Specifically, a traversal method may be used to compare each historical expression value with the expression value of the processor one by one, and after all comparisons, select the historical expression value with the smallest error with the expression value.

For step S503, after selecting a historical expression value closest to the expression value of the front processor, it is necessary to determine whether the error between the historical expression value and the expression value of the front processor is within a preset range. Inside. It can be understood that if the historical expression value and the processing person's expression value are within a preset range, it means that the historical expression value is close enough to the processing person's expression value, so that the historical approval corresponding to the historical expression value can be approved. Opinions are applied to the current approval work event. The preset range may be specifically determined according to actual use conditions, for example, it may be set to 10%, that is, an error between the selected historical expression value and the expression value of the person in front of the treatment is within 10%. The historical expression value is considered to be sufficiently close to the expression value of the processing person.

For step S504, if the error between the selected historical expression value and the expression value of the front processor is within a preset range, it means that the historical expression value is sufficiently close to the expression value of the front processor. The historical approval opinion corresponding to the historical expression value can be used as the approval opinion for this work event.

S104. Enter the approval opinion into the approval window.

After obtaining the approval opinion of this approval work, the method of this embodiment will also automatically input the approval opinion into the approval window, so that the processor can view the automatically entered approval opinion and consider whether it is appropriate. If appropriate, the processor clicks the "Submit" button to complete the submission of the approval opinion.

As can be seen from the above, the method of this embodiment can be implemented: the processor opens the approval window to approve the work event, the processor displays the corresponding expression or head movement after reading the content of the work event, and the server automatically recognizes the processor's approval The comments are entered into the approval window. After the processor sees the approval comments that are automatically entered, if the processor needs to modify them, the processor manually modifies the corresponding content, and then clicks the "Submit" button to submit to complete the approval process. The processor directly clicks the "Submit" button to submit and completes the approval process.

In order to more accurately judge the attitude of the processor on the approved work event, the method can also be combined with the head movement of the processor during the approval. It can be known that if the nod action occurs when the processor approves the work event, it is very likely that the processor agrees with the work event; on the contrary, if the shaker action appears when the processor approves the work event, it is very likely that the process People are opposed to work incidents. Therefore, further, as shown in FIG. 7, the method for automatically inputting an approval opinion may further include:

S601. Collect continuous face images of a processing person in front of a display screen of the target terminal;

S602: Obtain the head motion of the front-processing person according to the continuous face image analysis;

S603. Determine an attitude value corresponding to the head movement according to a preset movement attitude relationship. The movement attitude relationship records a correspondence relationship between the head movement and the attitude value.

With regard to the above steps S601 to S603, it can be understood that, by combining multiple continuous face images, it can be analyzed and known whether the processing person has made a head motion such as nodding or shaking his head. Particularly, in this embodiment, if the head of the processing person in the continuous face image has no movement, the head motion of the front processing person can be analyzed to be “immovable”. Accordingly, in the relationship of action attitude The attitude value of the "moving" head movement can be set to 0, which means that the "moving" head movement of the processor cannot reflect the attitude of the processor towards the work event. When the person's head movement is other movements, such as nodding or shaking his head, the attitude value determined according to the attitude relationship of the movement will be used as a factor to determine the approval opinion in step 103 below. Specifically, in an application scenario, the attitude value corresponding to the head movement of the "nodding" may be positive, and the attitude value corresponding to the head movement of the "shaking head" may be negative.

Based on the above steps S601 to S603, step S103 is specifically: determining the approval opinion of the front processor according to the corresponding relationship of attitude and opinion, and the corresponding relationship of the attitude and opinion records the corresponding relationship between the expression value, the attitude value, and the approval opinion. It is understandable that the attitude value corresponding to the head action of the processor can assist in assessing the true approval opinion of the processor. When the attitude value is positive, it means that the head movement of the processor reflects the processor's attitude to the approval opinion. Positive; when the attitude value is negative, it means that the processor's head movement reflects that the processor's attitude to the approval opinion is negative. Therefore, specifically, the corresponding relationship of the attitude and opinion can record the correspondence between the new expression value and the approval opinion, and the new expression value = the expression value + the attitude value, so when determining the approval opinion, first calculate the expression value and attitude of the processor The sum of the values is used to obtain a new expression value, and then the corresponding relationship of the attitude and opinion is obtained to obtain the approval opinion corresponding to the new expression value. It can be considered that the query approval opinion is the processor's approval opinion for the work event.

Further, before step S101, the method can also identify the processor, and determine whether the processor in front of the display screen of the target terminal has the authority to approve the current working time. If so, execute step S101; if not, reject all The front processor approves the work event. It can be understood that, because this method involves approval work, and the scheme itself is related to the processing habits of the processor, it is also possible to identify the processor before the automatic recognition and input of approval opinions, and the legality corresponding to different target terminals The processors can be different, and only those with a valid identity can use the corresponding target terminal for approval.

From the above, it can be known that the method for automatically inputting an approval opinion provided in this embodiment can automatically identify the approval attitude of the processor and determine the corresponding approval opinion, and automatically input the approval opinion into the approval window, reducing the organizational language of the processor, The burden of inputting approval opinions saves the processor time for processing approval work and improves the efficiency of approval work.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

In one embodiment, a device for automatically inputting an approval opinion is provided. The device for automatically inputting an approval opinion corresponds to the method for automatically entering an approval opinion in the above embodiment. As shown in FIG. 8, the apparatus for automatically inputting an approval opinion includes a face image acquisition module 701, an expression value analysis module 702, an approval opinion determination module 703, and an opinion input module 704. The detailed description of each function module is as follows:

A face image acquisition module 701, configured to collect a face image of a person in front of a display screen of the target terminal when it is detected that the front window of the target terminal is an approval window for a work event;

An expression value analysis module 702 is configured to analyze the face image by using an expression recognition technology to obtain an expression value of the front processing person, where the expression value reflects the approval attitude of the front processing person to the work event;

The approval opinion determining module 703 is configured to determine an approval opinion corresponding to the expression value of the front processor according to the corresponding relationship of the expression opinion, and the corresponding relationship of the expression opinion records the corresponding relationship between the expression value and the approval opinion;

The opinion input module 704 is configured to input the approval opinion into the approval window.

Further, the approval opinion determination module may include:

The interval falling determination unit is configured to determine, from preset preset expression value intervals, an expression value interval in which the expression value of the person in front of the processing falls, and each expression value interval is preset and separately associated with each preset Correspondence to approval opinions;

The opinion obtaining unit is configured to obtain an approval opinion corresponding to the determined expression value interval.

Further, each expression value interval may be determined in advance by the following modules:

A historical opinion obtaining module, configured to obtain each historical approval opinion and the facial expression value corresponding to each historical approval opinion when the front processor's historical approval work event;

The opinion classification module is configured to classify each historical approval opinion according to the approval attitude corresponding to the content of the historical approval opinion to obtain each opinion category;

An expression value interval determination module is configured to determine each expression value interval corresponding to each of the opinion categories, and a boundary value of the expression value interval is an expression value corresponding to a historical approval opinion in an opinion category corresponding to the expression value interval. determine.

Further, the device for automatically inputting an approval opinion may further include:

A continuous image acquisition module, configured to acquire a continuous face image of a processing person in front of a display screen of the target terminal;

A head motion analysis module, configured to obtain a head motion of the front-processing person according to the continuous face image analysis;

An attitude value determination module, configured to determine an attitude value corresponding to the head movement according to a preset movement attitude relationship, and the movement attitude relationship records a correspondence relationship between the head movement and the attitude value;

The approval opinion determination module is specifically configured to determine the approval opinion of the front processor according to the corresponding relationship of attitude and opinion, and the corresponding relationship of the attitude and opinion records the corresponding relationship between the expression value, the attitude value, and the approval opinion.

Further, the device for automatically inputting an approval opinion may further include:

A historical facial expression value acquisition module, configured to acquire each historical facial expression value collected during the historical approval work event of the front processor;

The closest expression value selection module is configured to select, from the historical expression values, a historical expression value that is closest to the expression value of the person in front of the processing;

An error judging module, configured to judge whether an error between the selected historical expression value and the expression value of the person in front of the processing is within a preset range;

A triggering module, configured to trigger the approval opinion determination module if the determination result of the error determination module is no;

The determination opinion module is configured to determine the historical approval opinion corresponding to the selected historical expression value as the approval opinion for the work event if the judgment result of the error judgment module is yes.

For the specific limitation of the device for automatically inputting an approval opinion, refer to the limitation on the method for automatically inputting an approval opinion above, which is not repeated here. Each module in the above-mentioned device for automatically inputting approval opinions may be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules may be embedded in the hardware in or independent of the processor in the computer device, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 9. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in a non-volatile storage medium. The database of the computer equipment is used to store the data involved in the method of automatically entering approval opinions. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer-readable instructions are executed by a processor to implement a method for automatically entering approval opinions.

In one embodiment, a computer device is provided, which includes a memory, a processor, and computer-readable instructions stored on the memory and executable on the processor. When the processor executes the computer-readable instructions, the processor automatically implements the above-mentioned embodiments. Steps of the method for inputting approval opinions, for example, steps S101 to S104 shown in FIG. 2. Alternatively, when the processor executes the computer-readable instructions, the functions of the modules / units of the apparatus for automatically inputting approval opinions in the above embodiments are implemented, for example, the functions of modules 701 to 704 shown in FIG. 8. To avoid repetition, we will not repeat them here.

In one embodiment, a computer-readable storage medium is provided, the one or more non-volatile storage mediums storing computer-readable instructions, and the computer-readable instructions are executed by one or more processors. , So that when one or more processors execute computer-readable instructions, the steps of the method for automatically inputting approval opinions in the foregoing method embodiment are implemented, or the one or more non-volatile readable storages storing computer-readable instructions Medium, when the computer-readable instructions are executed by one or more processors, causing the one or more processors to execute the computer-readable instructions to realize the functions of each module / unit in the apparatus for automatically inputting an approval opinion in the above device embodiment. To avoid repetition, we will not repeat them here.

A person of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by using computer-readable instructions to instruct related hardware. The computer-readable instructions can be stored in a nonvolatile computer In the readable storage medium, the computer-readable instructions, when executed, may include the processes of the embodiments of the methods described above. Wherein, any reference to the storage, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile storage. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

Those skilled in the art can clearly understand that, for the convenience and brevity of the description, only the above-mentioned division of functional units and modules is used as an example. In practical applications, the above functions can be assigned by different functional units, Module completion, that is, dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above.

The above-mentioned embodiments are only used to describe the technical solution of the present application, but not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still implement the foregoing implementations. The technical solutions described in the examples are modified, or some of the technical features are equivalently replaced; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the application, and should be included Within the scope of this application.

Claims (20)

1. A method for automatically inputting approval opinions, which is characterized by:

   When it is detected that the front window of the target terminal is an approval window for a work event, collecting a face image of a processing person in front of the display of the target terminal;

   Use facial expression recognition technology to analyze the face image to obtain facial expression values of the front processing person, the facial expression values reflecting the front processing person's approval attitude towards the work event;

   Determining an approval opinion corresponding to the expression value of the front processor according to the corresponding relationship of the expression opinion, and the corresponding relationship of the expression opinion records the corresponding relationship between the expression value and the approval opinion;

   The approval opinions are input into the approval window.
2. The method for automatically inputting an approval opinion according to claim 1, wherein the determining an approval opinion corresponding to an expression value of the front processor according to the correspondence relationship of the expression opinions comprises:

   Determining an expression value interval in which the expression value of the person in front of the processing falls, among the preset expression value intervals, each expression value interval being preset and corresponding to each preset approval opinion;

   Obtain an approval opinion corresponding to the determined expression value interval.
3. The method for automatically inputting an approval opinion according to claim 2, wherein each of the expression value intervals is determined in advance by the following steps:

   Acquiring each historical approval opinion and the expression value corresponding to each historical approval opinion when the front processor's historical approval work event occurs;

   Classify each historical approval opinion according to the approval attitude corresponding to the content of the historical approval opinion, and obtain each opinion category;

   Each expression value interval corresponding to each of the opinion types is determined, and the boundary value of the expression value interval is determined by the expression value corresponding to the historical approval opinion in the opinion category corresponding to the expression value interval.
4. The method for automatically inputting an approval opinion according to claim 1, wherein the method for automatically inputting an approval opinion further comprises:

   Collecting continuous face images of a processing person in front of a display screen of the target terminal;

   Obtaining the head motion of the front-processing person according to the continuous face image analysis;

   Determining an attitude value corresponding to the head movement according to a preset movement attitude relationship, and the movement attitude relationship records a correspondence relationship between the head movement and the attitude value;

   The determining the approval opinion corresponding to the expression value of the front processor according to the correspondence relationship of the expression opinion is specifically: determining the approval opinion of the front processor according to the correspondence relationship of the attitude opinion, which records the expression value, Correspondence between attitude values and approval opinions.
5. The method for automatically inputting an approval opinion according to any one of claims 1 to 4, before determining an approval opinion corresponding to an expression value of the front processor according to the correspondence relationship of the expression opinions, further comprising:

   Acquiring each historical expression value collected in the historical processing work event of the front processor in advance;

   Selecting a historical expression value closest to the expression value of the person in front of the processing from the historical expression values;

   Judging whether the error between the selected historical expression value and the expression value of the person in front of the processing is within a preset range;

   If the error between the selected historical expression value and the expression value of the front processor is not within a preset range, the determination of an approval opinion corresponding to the expression value of the front processor is performed according to the corresponding relationship of the expression comments. step;

   If the error between the selected historical expression value and the expression value of the front processor is within a preset range, the historical approval opinion corresponding to the selected historical expression value is determined as the work event Approval opinion.
6. A device for automatically inputting approval opinions is characterized in that it includes:

   A face image acquisition module, configured to collect a face image of a person in front of a display screen of the target terminal when it is detected that the front window of the target terminal is an approval window for a work event;

   An expression value analysis module, configured to analyze the face image by using expression recognition technology to obtain an expression value of the front processor, the expression value reflects the approval attitude of the front processor to the work event;

   The approval opinion determination module is configured to determine an approval opinion corresponding to the expression value of the front processor according to the corresponding relationship of the expression opinion, where the corresponding relationship of the expression opinion records the corresponding relationship between the expression value and the approval opinion;

   An opinion input module is configured to input the approval opinions into the approval window.
7. The apparatus for automatically inputting an approval opinion according to claim 6, wherein the approval opinion determination module comprises:

   The interval falling determination unit is configured to determine, from preset preset expression value intervals, an expression value interval in which the expression value of the person in front of the processing falls, and each expression value interval is preset and separately associated with each preset Correspondence to approval opinions;

   The opinion obtaining unit is configured to obtain an approval opinion corresponding to the determined expression value interval.
8. The device for automatically inputting an approval opinion according to claim 7, wherein each of the expression value intervals is determined in advance by the following modules:

   A historical opinion obtaining module, configured to obtain each historical approval opinion and the facial expression value corresponding to each historical approval opinion when the front processor handles the historical approval work event;

   The opinion classification module is configured to classify each historical approval opinion according to the approval attitude corresponding to the content of the historical approval opinion to obtain each opinion category;

   An expression value interval determination module is configured to determine each expression value interval corresponding to each of the opinion categories, and a boundary value of the expression value interval is an expression value corresponding to a historical approval opinion in an opinion category corresponding to the expression value interval. determine.
9. The device for automatically inputting an approval opinion according to claim 6, wherein the device for automatically inputting an approval opinion further comprises:

   A continuous image acquisition module, configured to acquire a continuous face image of a processing person in front of a display screen of the target terminal;

   A head motion analysis module, configured to obtain a head motion of the front-processing person according to the continuous face image analysis;

   An attitude value determination module, configured to determine an attitude value corresponding to the head movement according to a preset movement attitude relationship, and the movement attitude relationship records a correspondence relationship between the head movement and the attitude value;

   The approval opinion determination module is specifically configured to determine the approval opinion of the front processor according to the corresponding relationship of attitude and opinion, and the corresponding relationship of the attitude and opinion records the corresponding relationship between the expression value, the attitude value, and the approval opinion.
10. The device for automatically inputting an approval opinion according to any one of claims 6 to 9, wherein the device for automatically inputting an approval opinion further comprises:

    A historical facial expression value acquisition module, configured to acquire each historical facial expression value collected during the historical approval work event of the front processor;

    The closest expression value selection module is configured to select, from the historical expression values, a historical expression value that is closest to the expression value of the person in front of the processing;

    An error judging module, configured to judge whether an error between the selected historical expression value and the expression value of the person in front of the processing is within a preset range;

    A triggering module, configured to trigger the approval opinion determination module if the determination result of the error determination module is no;

    The determination opinion module is configured to determine the historical approval opinion corresponding to the selected historical expression value as the approval opinion for the work event if the judgment result of the error judgment module is yes.
11. A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, and is characterized in that the processor implements the computer-readable instructions as follows step:

    When it is detected that the front-end window of the target terminal is an approval window for a work event, collecting a face image of a person in front of the display screen of the target terminal;

    Use facial expression recognition technology to analyze the face image to obtain facial expression values of the front processing person, the facial expression values reflecting the front processing person's approval attitude towards the work event;

    Determining an approval opinion corresponding to the expression value of the front processor according to the corresponding relationship of the expression opinion, and the corresponding relationship of the expression opinion records the corresponding relationship between the expression value and the approval opinion;

    The approval opinions are input into the approval window.
12. The computer device according to claim 11, wherein the determining an approval opinion corresponding to an expression value of the person in front of the processing according to the expression opinion correspondence relationship comprises:

    Determining an expression value interval in which the expression value of the person in front of the processing falls, among the preset expression value intervals, each expression value interval being preset and corresponding to each preset approval opinion;

    Obtain an approval opinion corresponding to the determined expression value interval.
13. The computer device according to claim 12, wherein each expression value interval is determined in advance by the following steps:

    Acquiring each historical approval opinion and the expression value corresponding to each historical approval opinion when the front processor's historical approval work event occurs;

    Classify each historical approval opinion according to the approval attitude corresponding to the content of the historical approval opinion, and obtain each opinion category;

    Each expression value interval corresponding to each of the opinion types is determined, and the boundary value of the expression value interval is determined by the expression value corresponding to the historical approval opinion in the opinion category corresponding to the expression value interval.
14. The computer device according to claim 11, wherein the processor further implements the following steps when executing the computer-readable instructions:

    Collecting continuous face images of a processing person in front of a display screen of the target terminal;

    Obtaining the head motion of the front-processing person according to the continuous face image analysis;

    Determining an attitude value corresponding to the head movement according to a preset movement attitude relationship, and the movement attitude relationship records a correspondence relationship between the head movement and the attitude value;

    The determining the approval opinion corresponding to the expression value of the front processor according to the correspondence relationship of the expression opinion is specifically: determining the approval opinion of the front processor according to the correspondence relationship of the attitude opinion, which records the expression value, Correspondence between attitude values and approval opinions.
15. The computer device according to any one of claims 11 to 14, wherein the processor executes the computer before determining an approval opinion corresponding to an expression value of the front processor according to an expression opinion correspondence relationship. The following steps are also implemented when the instructions are readable:

    Acquiring each historical expression value collected in the historical processing work event of the front processor in advance;

    Selecting a historical expression value closest to the expression value of the person in front of the processing from the historical expression values;

    Judging whether the error between the selected historical expression value and the expression value of the person in front of the processing is within a preset range;

    If the error between the selected historical expression value and the expression value of the front processor is not within a preset range, the determination of an approval opinion corresponding to the expression value of the front processor is performed according to the corresponding relationship of the expression comments. step;

    If the error between the selected historical expression value and the expression value of the front processor is within a preset range, the historical approval opinion corresponding to the selected historical expression value is determined as the work event Approval opinion.
16. One or more non-volatile readable storage media storing computer readable instructions, characterized in that when the computer readable instructions are executed by one or more processors, the one or more processors are caused to execute The following steps:

    When it is detected that the front window of the target terminal is an approval window for a work event, collecting a face image of a processing person in front of the display of the target terminal;

    Use facial expression recognition technology to analyze the face image to obtain facial expression values of the front processing person, the facial expression values reflecting the front processing person's approval attitude towards the work event;

    Determining an approval opinion corresponding to the expression value of the front processor according to the corresponding relationship of the expression opinion, and the corresponding relationship of the expression opinion records the corresponding relationship between the expression value and the approval opinion;

    The approval opinions are input into the approval window.
17. The non-volatile readable storage medium according to claim 16, wherein the determining the approval opinion corresponding to the expression value of the front processor according to the expression opinion correspondence relationship comprises:

    Determining an expression value interval in which the expression value of the person in front of the processing falls, among the preset expression value intervals, each expression value interval being preset and corresponding to each preset approval opinion;

    Obtain an approval opinion corresponding to the determined expression value interval.
18. The non-volatile readable storage medium according to claim 17, wherein each expression value interval is determined in advance by the following steps:

    Acquiring each historical approval opinion and the expression value corresponding to each historical approval opinion when the front processor's historical approval work event occurs;

    Classify each historical approval opinion according to the approval attitude corresponding to the content of the historical approval opinion, and obtain each opinion category;

    Each expression value interval corresponding to each of the opinion types is determined, and the boundary value of the expression value interval is determined by the expression value corresponding to the historical approval opinion in the opinion category corresponding to the expression value interval.
19. The non-volatile readable storage medium according to claim 16, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors further perform the following steps:

    Collecting continuous face images of a processing person in front of a display screen of the target terminal;

    Obtaining the head motion of the front-processing person according to the continuous face image analysis;

    Determining an attitude value corresponding to the head movement according to a preset movement attitude relationship, and the movement attitude relationship records a correspondence relationship between the head movement and the attitude value;

    The determining the approval opinion corresponding to the expression value of the front processor according to the correspondence relationship of the expression opinion is specifically: determining the approval opinion of the front processor according to the correspondence relationship of the attitude opinion, which records the expression value, Correspondence between attitude values and approval opinions.
20. The non-volatile readable storage medium according to any one of claims 16 to 19, characterized in that before determining an approval opinion corresponding to an expression value of the front processor according to an expression opinion correspondence relationship, the When the computer-readable instructions are executed by one or more processors, the one or more processors further perform the following steps:

    Acquiring each historical expression value collected in the historical processing work event of the front processor in advance;

    Selecting a historical expression value closest to the expression value of the person in front of the processing from the historical expression values;

    Judging whether the error between the selected historical expression value and the expression value of the person in front of the processing is within a preset range;

    If the error between the selected historical expression value and the expression value of the front processor is not within a preset range, the determination of an approval opinion corresponding to the expression value of the front processor is performed according to the corresponding relationship of the expression comments. step;

    If the error between the selected historical expression value and the expression value of the front processor is within a preset range, the historical approval opinion corresponding to the selected historical expression value is determined as the work event Approval opinion.

Images