CN114628007A

CN114628007A - Emotion information processing system and method

Info

Publication number: CN114628007A
Application number: CN202210232581.6A
Authority: CN
Inventors: 吴丹
Original assignee: Qianjin Network Information Technology (shanghai) Co ltd
Current assignee: Qianjin Network Information Technology (shanghai) Co ltd
Priority date: 2022-03-09
Filing date: 2022-03-09
Publication date: 2022-06-14

Abstract

The invention relates to an emotion information processing system and method, wherein the system comprises: the information collection module is used for acquiring original information related to the emotion of the employee according to the personal identity of the employee; an emotional event extraction module, connected to the information collection module, configured to extract emotional events from the original information; the emotion index acquisition module is connected with the emotion event extraction module and is configured to process the extracted emotion events according to a configured processing strategy so as to obtain emotion index data of the staff; and an application module, connected to the emotion indicator acquisition module, configured to obtain follow-up advice applied to the employee according to preset application conditions based on the emotion indicator data. The invention improves the utilization efficiency of the related information of the employees in the enterprise, reduces omission or misjudgment caused by dependence on human experience and sensitivity, and avoids the influence of human subjective factors on the emotion judgment of the employees.

Description

Emotion information processing system and method

Technical Field

The invention relates to the technical field of data processing, in particular to a system and a method for processing emotion information of enterprise employees.

Background

With the development of society, the living pressure of people is greater and greater, and most people can have more or less emotional problems regularly and irregularly. The negative emotion which cannot be released seriously affects the physical health of individuals and also affects the society, the work and the surrounding people.

As the emotional problems are paid more and more attention by people, enterprises composed of staff members pay more and more attention to the emotional problems, and enterprise managers are aware that the emotions of the staff can have a significant influence on the overall performance of the enterprises from various aspects. The positive emotion of the staff usually generates positive effects in the enterprise organization, such as improving the work satisfaction of the staff, improving the team cooperation efficiency, enabling the staff in the team to show more relative organization behaviors, improving the willingness of the staff to actively improve the work flow and performance, improving the work performance of the staff in the enterprise, improving the overall innovation capability of the enterprise, and the like; on the contrary, negative emotions can produce negative effects in enterprise organizations, and researches show that although the positive relationship between the active emotions and the positive results of employees is not direct and obvious, the negative emotions of the employees can also produce a plurality of adverse effects, for example, compared with the employees with more active emotions, the employees with more negative emotions have lower work satisfaction degree and higher avoidance behaviors and job leaving tendencies, and are easier to cause contradictions among team members, so that the overall performance output of the team is reduced.

Although there are some solutions for managing or monitoring the mood of an individual, these solutions are mainly applied to an individual and are not suitable for an enterprise. For example, chinese patent application with publication number CN112885432A entitled "an emotion analysis management system" provides a solution for solving the problem that diagnosis accuracy is affected because emotional users are affected by tone, expression, action, language, etc. when facing a doctor, they cannot truly express their mind. Also, for example, chinese patent application publication No. CN105615902A entitled "emotion monitoring method and apparatus" provides a scheme for determining a user's emotion and emotional stimulus source by collecting the content output by a terminal being used by the user, that is, the physiological information and expression of the user collected by a sensor, an image collector, and the like. There are other disclosed schemes, such as those for obtaining and analyzing the emotion of the vehicle driver, the emotion of family members, etc., which are not described in detail herein.

In actual enterprise management operations, the recognition and understanding of the emotion of the employee by the enterprise managers are based on the observation of the enterprise managers themselves, which often depends on the personal experience and sensitivity of the managers, and is easy to miss or misjudge, so that the expected effect cannot be obtained. Based on the important influence of the emotion of the employee on the enterprise operation, a scheme capable of timely discovering and effectively managing the emotion of the employee is needed.

Disclosure of Invention

Aiming at the technical problems in the prior art, the invention provides an emotion information processing system and method, which are used for obtaining the emotion state of enterprise employees so as to timely intervene on the emotions of the employees when needed.

In order to solve the technical problem, according to one aspect of the present invention, there is provided an emotion information processing system, including an information collection module, an emotion event extraction module, an emotion index acquisition module, and an application module, wherein the information collection module is configured to acquire original information related to an emotion of an employee according to a personal identification of the employee; the emotion event extraction module is connected with the information collection module and is configured to extract emotion events from the original information; the emotion index acquisition module is connected with the emotion event extraction module and is configured to process the extracted emotion events according to a configured processing strategy so as to obtain emotion index data of the staff; the application module is connected with the emotion index acquisition module and is configured to acquire follow-up suggestions applied to the employees according to preset application conditions based on the emotion index data.

In order to solve the above technical problem, according to an aspect of the present invention, there is provided an emotion information processing method including the steps of: acquiring original information related to the emotion of the employee according to the personal identity of the target employee; extracting emotional events from the original information; processing the extracted emotion events according to a configured processing strategy to obtain emotion index data of the staff; and obtaining follow-up suggestions applied to the employees according to preset application conditions based on the emotion index data.

The invention collects the public information with hidden employee emotion trace from the system database under the premise of respecting and protecting employee privacy, and expresses the emotion state of the employee by processing the information into measurable indexes, thereby not only fully improving the utilization efficiency of the employee information in the enterprise, reducing omission or misjudgment caused by dependence on human experience and sensitivity, but also avoiding the influence of human subjective factors on employee emotion judgment, improving the scientificity and reproducibility of the enterprise on employee emotion management, and achieving the purpose of improving the emotion of the employee by timely intervening on the employee with negative emotion.

Drawings

Preferred embodiments of the present invention will now be described in further detail with reference to the accompanying drawings, in which:

FIG. 1 is a functional block diagram of an emotional information processing system provided according to an embodiment of the invention;

FIG. 2 is a functional block diagram of an information collection module provided according to one embodiment of the present invention;

FIG. 3 is a functional block diagram of an emotional event extraction module provided according to an embodiment of the invention;

FIG. 4 is a functional block diagram of an emotion indicator acquisition module provided according to an embodiment of the present invention;

FIG. 5 is a functional block diagram of a computing unit provided in accordance with one embodiment of the present invention;

FIG. 6 is a functional block diagram of a computing unit provided in accordance with another embodiment of the present invention;

FIG. 7 is a functional block diagram of an application module provided in accordance with an embodiment of the present invention;

FIG. 8 is a functional block diagram of an emotional information processing system provided according to another embodiment of the invention;

FIG. 9 is a functional block diagram of an emotion information processing system provided in accordance with yet another embodiment of the present invention;

fig. 10 is a flowchart of an emotional information processing method provided according to an embodiment of the present invention;

FIG. 11 is a flow diagram of a method of obtaining sentiment indicator data according to one embodiment of the present invention;

FIG. 12 is a functional block diagram of an application of an emotional information processing system provided according to an embodiment of the invention; and

fig. 13 is a structural connection diagram of an emotion information processing system provided according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In the following detailed description, reference is made to the accompanying drawings that form a part hereof and in which is shown by way of illustration specific embodiments of the application. In the drawings, like numerals describe substantially similar components throughout the different views. Various specific embodiments of the present application are described in sufficient detail below to enable those skilled in the art to practice the teachings of the present application. It is to be understood that other embodiments may be utilized and structural, logical or electrical changes may be made to the embodiments of the present application.

For the identification, recording and management of the emotion of the enterprise staff, the prior art is more based on the own observation and knowledge storage of the enterprise staff, which often depends on the personal experience and sensitivity of the staff. The management mode based on the personal experience and the characteristics of the management personnel has many defects, such as that the key emotion of the staff in the work is easily missed, even the emotion of the staff is misread, and further the emotion management and the intervention work of the staff are negatively affected.

Meanwhile, some management systems used by most enterprises, such as human resource management systems, record a large amount of information about the employees of the enterprises in the daily operation process, such as attendance data, work performance data, various information fed back through the system, and the like, wherein the information usually implies the trace of the emotion of the employee, or the information usually has clues indicating the current and future emotion changes of the employee. However, the management systems relied on or used by current enterprises rarely mine the clues or traces capable of effectively revealing the emotional states of the employees scientifically and in detail, and further lack methods and systems for scientifically analyzing the clues or traces and providing comprehensive and effective employee emotional management suggestions for managers on the basis of the clues or traces, so that the management systems used by current enterprises cannot effectively and scientifically record, analyze and manage the emotional states of the employees of the enterprises. Aiming at the problems, the invention provides a system and a method for processing staff emotion information.

The staff leaves emotional traces everywhere in the process of working, learning and daily life, or there are clues indicating the future emotional changes of the staff everywhere, the auxiliary management system relied or used by the current enterprise mainly collects attribute data (such as age, academic calendar, education condition and the like) related to personnel and various performance related data (such as attendance, work efficiency, work quality and the like), but rarely carries out scientific and detailed record on clues or traces which can effectively reveal the emotional state of the personnel, and further lacks of carrying out scientific analysis on the clues or traces, and on the basis, a comprehensive and effective staff emotion management suggestion method and system are provided for management staff, so that the current management auxiliary system used by an enterprise cannot effectively and scientifically record, analyze and manage the emotion states of the staff of the enterprise.

Fig. 1 is a schematic block diagram of an emotion information processing system provided according to an embodiment of the present invention, which includes an information collection module 1, an emotion event extraction module 2, an emotion index acquisition module 3, and an information application module 4. The information collection module 1 obtains original information related to the emotion of the employee according to the personal identification of the employee. The emotional event extraction module 2 is connected to the information collection module 1, and is configured to extract an emotional event from the original information. The emotion index acquisition module 3 is connected with the emotion event extraction module 2 and is used for processing the extracted emotion events according to a processing strategy to obtain emotion index data of the staff. The information application module 4 is connected with the emotion index acquisition module 3, and acquires follow-up suggestions applied to the employees according to preset application conditions based on the emotion index data.

FIG. 2 is a functional block diagram of an information collection module provided in accordance with one embodiment of the present invention. In the present embodiment, the information collection module 1 includes one or more of the following units: a personal information collection unit 11, a interpersonal information collection unit 12, one or more feedback units 13, and one or more behavior information collection units 14. The units are connected with an enterprise human resource database and an enterprise comprehensive database to obtain various information required by the invention, and then store the obtained various original information, such as in an emotion database. Of course, in some cases, the human resource database and the integrated enterprise database are merged into one database, and the units of the present invention are connected to the single database. Alternatively, in an enterprise comprising a plurality of independent databases, the units of the invention are connected to the respective databases as required to obtain the required information. In this embodiment, the personal information collection unit 11 is connected to a human resources database of an enterprise. The enterprise human resource system in this embodiment includes various modules, such as an interview module, an attendance module, a training module, a performance module, a compensation welfare module, a geographic location module, and a task module. The modules in the human resource system have a corresponding logic processing function and a data collecting function, and store the collected data and information in the human resource database.

The interview module comprises an information collection unit, an interview evaluation unit and a distribution team unit, when a worker interviews by an interviewer before entering a company, a job seeker fills in a personal resume through the information collection unit, and therefore personal resume information filled in by the job seeker is collected. After the interview passes, the interviewer adds various initial labels to the staff through the interview evaluation unit and distributes the staff to the target team through the distribution team unit, wherein the initial labels added to the staff by the interviewer comprise the job number, the age, the work place, the position, the initial skill labels and the like. The interview module collects basic information of the staff, interview evaluation information and assigned team information, and stores the information in the human resource database.

The attendance module is a functional module for recording and managing attendance information of daily work, overtime, vacation and the like of the staff, wherein the daily attendance data, the overtime duration, the vacation use condition and the like of the staff are recorded. An attendance management unit in the attendance module records the attendance of the daily work of the staff, including the daily on-duty time and off-duty time; a scheduling management unit in the attendance module records the overtime arrangement and overtime duration of the staff; the vacation management unit in the attendance module records the accumulated available vacation days of the employee and the used vacation days. The attendance information is stored in a human resource database.

The training module is a functional module for performing certification management on employee training and skills, and preferentially arranges related skills which are not possessed by the employees before learning through the course management unit according to the initial skill labels of the employees so as to expand knowledge storage; after the staff completes the training of a certain skill, the result examination unit in the training module can automatically form the training and learning effect of examining the staff for examination and acceptance of test paper, wherein the examined question type comprises selection, judgment, actual operation, writing, game test and the like; after the staff passes the examination, a skill label unit in the training module can print a new skill label for the staff according to the training program participated by the staff; the skill tag information of the staff can be used as the basic performance of the staff and transmitted to the performance module for the analysis and settlement of the work performance of the staff. All relevant data for the various units described above are stored in the human resources database.

The performance module is a module comprehensively applied by personal information and performance information of the staff, and the performance settlement unit records the work completion efficiency and the work completion quality of the staff by taking a month as a unit, integrates, analyzes and evaluates the work scores of the staff and calculates the monthly original performance data of the staff; an index management unit in the performance module compares the performance of the employee estimated at the beginning of the month with the actual original performance data of the employee in the current month and gives the performance rating of the employee; and the performance supplementing unit in the performance module is used for independently recording a plurality of independent performance events expressed by the staff in the current month, and weighting the independent performance events on the performance rating of the staff after scoring. The data obtained by the units are also stored in the human resource database.

The salary welfare module receives the staff performance information transmitted by the performance module, simultaneously receives other staff basic information transmitted by the interview module, the attendance module and the training module, evaluates and manages the basic salary, performance bonus and welfare of the staff after comprehensively analyzing all information of the staff, provides direct reference for the manager to issue the staff salary welfare, and stores the data into the staff resource database.

The geographic position module is used for recording the geographic position of each employee during work, such as the city and the building, the building floor and the seat number. For example by a manager at the time of employee attendance or seat exchange, depending on the actual seat entry of the employee. The employee region unit in the geographic position module records the city and the building where the employees work, the employee floor unit in the geographic position module records the building floor where the employees work, and the employee seat unit in the geographic position module records the seat number of the employees, so that the geographic position of each employee can be positioned.

The task module is used for recording basic information of projects or tasks participated by the staff, duties/roles of the staff in the projects or tasks, total project progress information, staff task progress information and all communication record information of the staff in the process of the projects or tasks. Some of the information is entered by the manager, for example, the manager enters when the employee joins a specific project group, including basic information of the project or task, a specific project number in which the employee participates, and a role/role of the employee when the employee joins the specific project group. Some information is entered by the staff themselves, including the progress of their tasks, the communication records of active communication and passive communication, etc. And the task module can count the total progress information of the project according to the task progress information of each employee and the basic information of the project. All this information is stored in the human resources database.

In this embodiment, the personal information collection unit 11 is connected to the human resources database, and reads one or more of personal identification information, attendance information, performance information, training information, and compensation information of the employee from the human resources database, where the information includes information for calculating the emotional basic index.

Since the interpersonal relationship of a person with other people is an important factor affecting the mood of a person, the present invention further includes the interpersonal information collection unit 12 for collecting various interpersonal interaction information in the workplace. Specifically, the interpersonal information collection unit 12 includes a geographical location information collection subunit 121 and a task information collection subunit 122. The geographic location information collecting subunit 121 is configured to collect the geographic location information of the employee, where the geographic location information at least includes location layout information of a work place of the employee. The task information collecting subunit 122 is configured to collect the work information that the employee participates in, where the work information includes one or more of project and/or task basic information that the employee participates in, project and/or task progress record information, employee duty/role information in the project or task, employee weekly report text, and personnel exchange record information in the process of the project or task progress.

The feedback units 13 in this embodiment include two types, one type is a first feedback unit 131 used by an interviewer professional, such as a psychological consultant, a mental health professional or a manager engaged by an enterprise, and the interviewer professional periodically interviews the employee and inputs feedback information of the interview, including recent emotional events and emotional feedback information of the employee, via the first feedback unit according to the interview result. The feedback information can include written text information summarized by interviewer, and can also include interview recording files. In one embodiment, the first feedback unit 131 further has a data processing function. For example, the first feedback unit 131 is connected to other units/modules or an emotion database, and determines whether there are any events or information related to the emotion of the employee according to a preset type of collected information, for example, relevant information related to the business activity range (i.e., business-related group) of the employee is not queried in the emotion database, and makes an interview target according to the missing information and outputs the interview target to an interviewer, so as to prompt a professional mental health worker/manager to focus on the social situation of the employee with other employees during the work in the current time period, and the focus of the interview is on the social situation of the employee. The other is a second feedback unit 132 used by a manager or employee, e.g. an employee with certain authority, such as a certain level of manager, via which life events, emotional conditions, etc. observed or known to have recently occurred on the employee can be input into the system. For example, the manager gives the staff criticism of a plurality of rewards, work errors and the like in the ordinary management work, and for example, the manager observes flowers/gifts and times received by the staff and the like.

The behavior information acquisition unit 14 is used for acquiring public behavior information of the staff at a workplace; wherein, the public behavior information is the times/frequency of specific daily behaviors of the staff. For example, the comprehensive database stores workplace security monitoring video data, such as enterprise security monitoring videos collected in office hallways, aisles, halls of office buildings, or the system is connected with a database of a security monitoring system of a building where an enterprise is located, and the action behaviors of employees are identified from workplace security video pictures and are subjected to statistical induction to obtain the frequency or frequency of certain actions. For example, when a fixed station of an employee is located in an office hall with a security monitoring video, the behavior of the employee leaving the station is identified and the leaving times are counted; counting the number of times and frequency of phone calls of the employees; counting the smoking behavior, duration and times of the employees in the smoking area; counting the times of drinking coffee and the times of introducing water in the rest area of the staff, and the like. The public behaviors occurring in public places can reflect the emotions of employees to a certain extent, and specific emotional events can be determined by combining with other information or index data.

Wherein the information collecting module 1 further comprises a converting unit 15 configured to convert non-text information in the original information into text information, such as converting an interview recording file into a text file.

Fig. 3 is a functional block diagram of an emotional event extraction module provided according to an embodiment of the present invention. In this embodiment, the emotional event extraction module 2 further includes an emotional base indicator calculation unit 21 and an emotional event evaluation unit 22. The emotion basic index calculation unit 21 is configured to calculate emotion basic index data related to each type of original information based on the type of original information. The emotion basic index is an index for determining an emotional event. For example, corresponding to the emotional event "love", corresponding emotional base indicators include, but are not limited to, "not married," "number of times gift/flower is received," "number of times phone call is answered," "number of shifts/duration/frequency," "attendance facial recognition expression," and so forth. For example, the basic index of emotion corresponding to the emotional event "work dissatisfaction" is "compensation welfare information", "shift-adding times/duration/frequency", "communication type", "project progress", "task progress", "skill label coincidence rate of the group of employees related to the employee", "work competency degree", and the like.

The process of calculating or counting various emotion basic indexes includes: the method comprises the steps of obtaining the index data of the geographical activity range of the staff based on the position layout information of the work place of the staff, and obtaining one or more kinds of business index data of the staff based on the work information participated by the staff. The geographic activity range index and the business index are used as basic emotion indexes for representing interpersonal interaction.

The geographic activity range index includes multiple types, for example, according to the current working position number of the employee, the associated employee group with more than one activity range level is determined for each employee according to the working position distance, and the associated employee group with different activity range levels is used as the index data of the geographic activity range of each employee. For example, 8 employees around the employee are determined as their associated employee group, i.e., their geographic range of activity, based on the employee's current work location number. A plurality of employees directly adjacent to the employee seat can be used as the first level of geographic activity range, such as employees adjacent to the employee seat left and right, front and back, and the like. The number of employees in the first level of geographic range of activity may vary depending on the specific location of the employees and the layout of the distribution of the location of the employees.

The emotion basic index also comprises the employee business activity range. When the index data is calculated, firstly, the identity identifications and the responsibilities/roles of other employees of the same project and the same task are determined according to project or task basic data participated by the employees; and generating a project employee matrix table according to the employee identity and the duty/role of the same project and/or the same task, wherein the employee matrix table is used as the employee business activity range. Similar to the geographical activity range of the staff, a plurality of business activity ranges of different levels are determined from the staff matrix table according to the business distance relationship with the staff. For example, a person who has a direct business association with the employee is determined to be a first level business activity scope, e.g., each task group leader is the first level business activity scope of the project principal; the team members in each task group are the second level business activity scopes of the project principals.

The emotional base indicator also includes an overall progress of the project. When the index data is calculated, the time and the task information to be completed in the project progress index data are read, and compared with the currently completed task information, for example, 6 tasks should be completed at the current time point according to the progress expectation, but the number of the currently completed tasks is 5, so that 5/6 is 83%, and the current progress percentage value of the project is obtained, and is used as the total project progress index data.

The emotion basic indexes further comprise task progress and staff task progress. Calculating according to the current completion data and the expected completion target of the employee task to obtain a percentage value of the employee task progress, and taking the percentage value as the employee task progress index data; and taking the average value of the task progress index data of all the employees in one task as the task progress index data.

The emotional base indicators further include item complaint indicators. And counting the total complaint times, the tasks corresponding to each complaint and the corresponding staff from the project or task basic data, and counting the complaint times of the staff. These data are used as project complaint index data.

The emotion basic indexes further comprise communication indexes, and the related indexes comprise total exchange times, exchange times initiated/accepted by each employee, and the duration of each exchange, the number of the employees involved in each exchange and the number of the employees involved in each exchange.

The emotional base indicators also include performance gaps, which include the gaps between the staff individuals in various statistical periods, and also gaps with other staff, for example, the gaps between the staff and the average work performance of the related staff groups.

The emotion basic indexes further comprise age indexes, wherein the age indexes comprise the ages of the individuals of the employees, the age distribution and the age mean of the related employee groups, and the difference between the ages of the employees and the age mean.

The emotion basic indexes further comprise skill label coincidence rate. And calculating the skill label coincidence rate of the associated employee group where the employee is located according to the skill label data of each employee in the associated employee group, such as the percentage of the number of the same or similar skill labels to the total number of the skill labels of the associated employee group.

The emotion basic indexes further comprise communication types, communication ranges and cooperation conditions of the employees. For example, calculating the ratio of the number of exchanges initiated by the employee to the total number of exchanges; and then determining the communication type determined by the duty threshold value for the staff according to the duty ratio and the threshold value of the staff communication times. For example, when the ratio of the number of exchanges to the total number of exchanges of an employee is less than 30%, the employee is determined to be of the passive communication type, and when the ratio of the number of exchanges to the total number of exchanges is greater than or equal to 30%, the employee is determined to be of the active communication type. Calculating the ratio or difference of the percentage value of the current task progress of each employee to the percentage value of the task plan progress; and comparing the ratio or the difference with a threshold, and when the ratio or the difference is greater than or equal to the threshold and the number of complaints of the staff is greater than the threshold, determining that the index value of the cooperation situation of the staff is a problem, otherwise, determining that no problem exists. And determining the communication range of the staff according to the number and the staff who participate in the communication.

The emotion basic index further comprises: the marital state in the personal identity information determines marital indexes such as 'married/shown marriage/divorce/funeral couple' and the like; determining 'leaving time length' according to the original home address, the current working address and the vacation information; indexes such as 'working duration', 'concentration degree' and the like calculated according to the time and the frequency of card punching determined by the attendance information; calculating a current mood index and a mood index in a statistical period when the card is printed at present according to the facial expression in the attendance information; performance indexes influencing emotion can be calculated according to performance scores in the performance information; calculating the 'competence or difficulty degree' of the staff to work according to the training content and times in the training information; the skill labels in the training information can be used for calculating indexes such as 'skill matching degree' of colleagues around the workstation and colleagues in the same project. Obtaining other contents such as 'child education' indexes or 'child education' indexes and the like from interview feedback information; acquiring index data of 'clothes tidiness' through the clothes information monitored by the video; obtaining 'frequent smoking' index data through smoking behaviors monitored by videos; the 'working time emotion' index data obtained by observing the feedback information, and the like.

Determining the unmarried state of the staff based on the marital information in the personal information, and calculating according to the received flowers/gifts and times obtained by the second feedback unit to obtain love index data; calculating to obtain work satisfaction index data based on the overtime length and the salary welfare information in the staff attendance data; calculating to obtain work difficulty index data based on the overtime length in the staff attendance data, the training times and content in the training information, and the performance score and the progress data of the work task in the performance data; family casualty index data and the like are calculated based on the number/frequency of times of staff leaving a work station, the number/frequency of times of answering calls, the number of absent days in attendance data, the progress of work tasks and the like. The basic emotion indexes and the calculation logic thereof can be updated and supplemented at any time by managers, specially-assigned persons and the like so as to continuously improve the index data capable of determining the emotional events.

The emotional event evaluation unit 22 is connected to the emotional base index calculation unit 21, and obtains one or more emotional events according to the obtained emotional base index. In one embodiment, the system database stores various emotional events and emotional metrics associated with the emotional events, as well as rules for determining the emotional events and trained machine learning models for evaluating a particular emotional event.

In some embodiments, the emotional base indicator data is evaluated based on one or more factors that determine an emotional event and a rule, and the emotional event may be determined when the emotional base indicator data meets the one or more factors that determine the emotional event or meets the rule. For example, for the emotional event "divorce," when divorce information is determined from currently obtained emotional basic index data and information that the original individual's marital status is "married" is combined, it can be determined that the emotional event "divorce" has occurred to the employee within the processing period. As another example, based on currently obtained emotion basic index data: the communication type of the staff is a passive communication type, the working post is a sales representative, the performance score is not up to the standard, and the task progress is delayed, so that emotional events such as dissatisfaction with work, difficulty in work, inadaptation to work and the like can be determined.

In other embodiments, for some complex emotional events, the evaluation may be performed by a trained machine learning model. For example, for the emotional event "hot love", according to the characteristics of the prediction sample, the basic indicators of emotion (such as the original marital state is "unmarried", "the number of times flowers are received/sent", "the number of times of photos in social circles/frequency/number of times of photos) corresponding to the characteristics are combined together to form the prediction sample, the prediction sample is input into the machine learning model, the machine learning model predicts the probability of hot love based on the multi-dimensional characteristic values in the prediction sample, and outputs whether the hot love and the different degrees of the hot love are present according to the set threshold value, so that the emotional event" hot love "can be obtained, and the specific severity value of the emotional event" hot love "can also be obtained at the same time. For example, for the emotional event "new person impact", the features of the prediction sample, such as "age", "age average of related employee group", "gap between age and age average of employee", "years of employment", "work post of related employee group", "role in project", etc., are used to predict whether or not there is an "new person impact" event based on the multidimensional feature values in the prediction sample by the machine learning model, and if there is any, an impact degree value is obtained.

The machine learning model can adopt any one algorithm of algorithms such as a decision tree, naive Bayes, multi-layer, k-nearest neighbor, random forest or neural network and the like.

In some embodiments, the emotional events may further include, but are not limited to: promotion, standing, awarding, etc., fatalities of relatives and friends, illness, parent dissimilarity, loss of love, family troubles, impact of new people, unsmooth rising and paying, too much workload, complex interpersonal relationship of workplaces, strict requirements of boss, very long working time, great fluctuation of emotion, bad cooperation with colleagues, urgent working transition time, lack of influence on decision/undefined role regulation, excessive regulation/unpleasant environment (such as high temperature, dim light, excessive noise, etc.), work movement, new job challenge, new leadership adaptation, lack of interpersonal communication, conflict with department/colleagues, assumed work exceeding personal ability category, illness, house dismantling, love or contract, failure of love, marriage, pregnancy, self (lover) abortion, family addition of new members, family members's incompatibility, The method comprises the following steps of divided living of couples, divorce, child's failure in learning (employment), child's administrative education difficulty, long-term departure of children, family economic difficulty, debt, remarkable improvement of economic conditions, starting employment, deduction of bonus or penalty, outstanding personal achievement, promotion, dissatisfaction with current work, poor work performance, work away from hometown, serious injury to disease and activity of friends, death of friends, misunderstanding/strange/35820, announcement/discussion, civil legal dispute intervention, detained, stolen/property loss, accidental scaring, accident occurrence and natural disaster.

The above events can be classified into major emotional events and minor emotional events according to event intensity classification. Major emotional events mainly refer to those major life changes causing great emotional intensity, such as marriage, dissimilarity, diseases, and the like. The small emotion events mainly refer to the events which are weak in emotional intensity but easy to stress, such as losing articles, being disturbed continuously, having insufficient leisure time and the like.

In one embodiment of the invention, the emotion event classification table is generated by summarizing various events which may occur in life and according to the strength of emotional influence and is stored in a database for use. The event nature and intensity value for each emotional event are included in the classification table. The event properties are divided into positive and negative, positive being represented by the number 1 and negative being represented by the number-1, representing a positive and negative impact on a person, respectively. The event intensity value is a preset classification standard according to the personal emotion influence of the staff, and the intensity value is a numerical value from 0 to 1.

Fig. 4 is a schematic block diagram of an emotion index acquisition module according to an embodiment of the present invention. In this embodiment, the emotion indicator obtaining module 3 includes an emotion event counting unit 31, a classifying unit 32 and a calculating unit 33, where the emotion event counting unit 31 counts the number/frequency or severity of occurrences of the emotion event in a counting period based on the obtained emotion event. For example, as shown in table one:

table one:

life event	Frequency of	Degree of freedom value
			Disease of illness	1	0.2
House dismantling	0	0.5
			Love	1	0.5
Promoting function	1	0.6
			Lost love	0	0.4
Prize receiving	3	0.3
			Pregnancy	0	0.5
Love of heat	1	0.5
			Impact of new person	0	0.2
Work satisfaction	1	0.8
			……	……	……

The classification unit 32 queries a classification table stored in a database based on the extracted emotional event, and further obtains classification data of the emotional event. In one embodiment, the classification data includes emotional event properties and intensity values. The event properties are divided into positive and negative, with positive being represented by the number 1 and negative being represented by the number-1. The event intensity value is a preset classification standard according to the influence on the personal emotion of the staff, the intensity value is a numerical value from 0 to 1, the larger the numerical value is, the larger the influence of the emotional event on the personal emotion of the staff is, and the following table II shows that:

a second table:

the professional mental health personnel or the manager of the enterprise can also adjust the nature and intensity value of the emotional event according to the actual condition of the enterprise. The classification unit 32 queries the classification table based on the extracted emotional event, and further obtains the event property and the intensity value of the emotional event, where the finally obtained data includes the emotional event, and the corresponding event property value N, the occurrence frequency value F, and the intensity value S.

The calculating unit 33 is connected to the classifying unit 32, and calculates the emotion index data of the employee based on the classification data and the statistical data of the emotional event.

In one embodiment, as shown in fig. 5, the calculation unit 33a calculates the employee's emotion index data based on a preset rule. In this embodiment, the calculating unit 33a includes an emotion coefficient calculating unit 331a and a cumulative emotion coefficient calculating unit 332 a. In this embodiment, the emotion coefficient is used to measure the emotion of the employee, where the emotion coefficient calculation unit 331a calculates the emotion coefficient p of a single statistical period, specifically by using the following formula 1-2:

wherein, the N is_iIs the property value, F, of the ith emotional event_iIs the frequency value of the occurrence of the ith emotional event, S_iAnd I is the intensity value of the ith emotional event, and the total number of emotional events in one statistical period is I. And after the property value, the frequency value and the intensity value of each emotional event are multiplied, summing the products of all the emotional events to serve as the emotion coefficient p of the current statistical period of the staff.

Preferably, the cumulative emotion coefficient calculation unit 332a calculates the emotion coefficients for a plurality of statistical periods, since the influence of emotional events on the emotion of the individual has a cumulative effect. In one embodiment, the cumulative effect amount of the emotional events of the employee in the last four statistical periods (for example, each statistical period is one month) is calculated to obtain a cumulative emotional coefficient P, the weight of the emotional event related value in the current month is the largest and is set to be a value 1, the weight of the emotional event related value in the last month is reduced to 0.7, the weight of the emotional event related value in the last two months is reduced to 0.4, and the weight of the emotional event related value in the last three months is reduced to 0.1, and the specific calculation formula is shown in formulas 1 to 3:

when the accumulated emotion coefficient P of the employee is a positive value, the accumulated emotion coefficient P represents that the emotion events bring main positive influence to the employee, and mainly cause the positive emotion of the employee, and the higher the numerical value is, the stronger the positive emotion intensity of the employee theoretically caused; when the emotion coefficient P of the employee is a negative value, the main negative influence on the employee caused by the emotional event is shown, the negative emotion of the employee is mainly caused, and the higher the value is, the stronger the negative emotion intensity of the employee is theoretically caused.

In other embodiments, the emotion of the employee is estimated through a trained machine learning model, each emotional event is used as a one-dimensional characteristic of a prediction sample, and the emotion coefficient p of each emotional event is used_iAs a feature value, a predicted sample is obtained. In these embodiments, as shown in fig. 6, the calculation unit 33b further includes a feature value operator unit 331b, a sample generation subunit 332b, and a predictor subunit 333 b. Wherein the feature value operator unit 331b calculates an emotional coefficient p of each emotional event according to formula 1-1 based on the classification data and the statistical data of the emotional events_i；

p_i＝N_iF_iS_iFormula 1-1

Wherein, the N is_iIs the property value, F, of the ith emotional event_iIs the frequency value of the occurrence of the ith emotional event, S_iThe intensity value for the ith emotional event.

The sample generation subunit 332b combines all the emotional events of the employee in one statistical period with the emotional coefficient of the emotional event as a feature value to obtain a prediction sample. The prediction subunit 333b inputs the prediction samples to the machine learning model to obtain the emotion index data of the target employee. The machine learning model can adopt any one algorithm of algorithms such as a decision tree, naive Bayes, multi-layer, k-nearest neighbor, random forest or neural network and the like, and the model obtains the emotion value based on the employee emotion event based on prediction of a prediction sample. In one embodiment, the output of the model may be set as a probability value of good emotion of the employee, the probability values representing the good emotion are respectively divided into different intervals by setting different probability thresholds, and the emotion is represented from bad to good according to the interval values from small to large. It is also possible to set the output of the model to a plurality of categories representing different emotions, the corresponding category being determined by calculating a probability of belonging to each category based on the predicted samples.

Fig. 7 is a functional block diagram of an application module provided in accordance with an embodiment of the present invention. In this embodiment, the application module 4 includes an employee emotion figure unit 41 and a follow-up advice generation unit 42. The employee emotion portrait unit 41 obtains emotion portrait data of the employee based on the employee's emotional event, emotion index data and/or emotion basic index data. The emotion portrait data serves as a comprehensive 'profile', can clearly and comprehensively represent the current emotional state of the employee in the enterprise, and can obtain potential emotional risks through further analysis. The follow-up suggestion generation unit 42 generates a corresponding follow-up suggestion based on the application condition and the corresponding processing policy. For example, the application condition includes data for judging whether one index data or a combination of index data is negative emotion. The data of negative emotions are, for example: the emotional coefficient or the cumulative emotional coefficient P is a negative value, the cumulative emotional coefficient of a certain emotional event is a negative value, and the like. When one or a combination of plural pieces of index data is data of a negative emotion, follow-up advice generating unit 42 reads a corresponding follow-up advice information template from the follow-up advice information template library, and modifies the original follow-up advice information on the template according to the current concrete data, thereby generating follow-up advice information that conforms to the current situation. The follow-up advice information is, for example, advice to further understand the relevant details of the employee's negative emotions and advice to alleviate the negative emotions. In one embodiment, different application information templates have suggestions for different negative emotion relief stored therein, such as "the employee has a high number of recent illness, interviews are concerned about the physical condition of the employee," "the employee has a high number of contradictions with surrounding colleagues in the recent past," the employee is scheduled to change seats, "" the employee is faced with difficulty in child management and education in the recent past, "interview is suggested for comfort, and necessary family parentage coaching is provided," "the employee has been working for a long time continuously, and the employee's emotional state is suggested to be observed and followed," and so on.

Fig. 8 is a functional block diagram of an emotion information processing system provided according to another embodiment of the present invention. In this embodiment, in order to display details such as the staff emotion indicators and staff emotion images, the display module 5 is further included on the basis of the foregoing embodiment, and is connected to the staff emotion image unit 41 and the follow-up suggestion generation unit 42 in the application module 4, and displays the details according to a set format, such as a pattern, a diagram, an image, and the like, and in cooperation with corresponding colors. For example, corresponding to the emotional events of the staff in the statistical period, when the display mode of the bar chart is adopted, each cylinder represents one emotional event, the emotional coefficient of a single emotional event is marked at the top end of each cylinder, and different colors are given to the cylinders according to the difference between the emotional coefficient and the threshold value representing the normal emotion. Different colors represent the influence of the emotional event on the emotional state of the employee, green represents positive influence on the employee, yellow represents negative emotional influence on the employee, red represents negative emotional influence on the employee, and darker colors represent stronger emotional influence on the employee, such as light green and light red, which represent stronger positive and negative emotions, respectively.

Similarly, the same display mode can be adopted for the constituent emotional events, the corresponding emotional basic index data and the final emotional coefficients. The emotion portrait data of each employee can be displayed, meanwhile, application information generated based on the emotion portrait of the employee can be marked beside the portrait, and after the professional mental health personnel/management personnel know the emotion state and potential risks which the employee may be in, suggestions on how to intervene and manage the employee can be obtained.

Fig. 9 is a functional block diagram of an emotion information processing system according to still another embodiment of the present invention. In this embodiment, a reminder module 6 is included in addition to the modules shown in fig. 1 or fig. 8. In one embodiment, the reminding module 6 is connected to the application module 4, and the application module 4 sends the finally obtained staff emotion index data to the reminding module 6. And the reminding module 6 judges whether the emotion index data of the staff meet reminding conditions according to preset rules. For example, when the staff emotion index data is a final emotion coefficient or a cumulative emotion system, which is a negative value, and an absolute value of the negative value is greater than or equal to a threshold, it indicates that the current staff emotion is not good, and immediate intervention is required, and at this time, a reminding message is generated and sent to related staff, such as a manager, a mental health specialist, and the like.

In another embodiment, the reminding module 6 is connected to the emotional event extraction module 2, and processes the extracted emotional event or emotional basic index data, and sends out a reminding message when the reminding condition is met. For example, when the emotional event extraction module 2 calculates some emotional basic index data, the reminding module 6 compares the emotional basic index data with a corresponding threshold or with a set condition, for example, when the obtained "frequent smoking" number exceeds the threshold, a reminding message of "needing interview" is generated to a special person, and a reason that the "smoking number is too frequent" is provided. For another example, when the number of times that the employee leaves the workstation, the number of absent days, and the like reach a threshold value, a reminder message of "meeting the need" is generated to the special person, and a corresponding reason is provided, and the like. Therefore, managers, psychological consultants, psychological health professionals and the like can arrange time to speak or communicate with the staff at any time when receiving the reminding messages and help the staff to solve the problem of generating negative emotions, so that the system provided by the invention can further acquire the information of generating the negative emotions of the staff at any time between the emotion index data of the staff obtained by twice calculation.

In another aspect, the present invention further provides an emotional information processing method, and fig. 10 is a flowchart of an emotional information processing method according to an embodiment of the present invention. The emotion information processing method comprises the following steps:

and step S1, acquiring original information related to the emotion of the employee according to the personal identification of the target employee. Wherein the original information related to the emotion of the employee comprises one or more of personal information of the employee, interpersonal interaction information, interview/observation feedback information of a specific person and public behavior information of the employee at the workplace. The personal information of the staff comprises personal identity information, attendance checking information, performance information, training information, compensation welfare information and the like extracted from a corporate human resource database and a corporate comprehensive database. The interpersonal interaction information comprises geographical position information and/or work information participated by employees, which are extracted from an enterprise human resource database and an enterprise comprehensive database. The geographical position information at least comprises position layout information of the employee workplace; the work information comprises one or more of project and/or task basic information participated by the staff, project and/or task progress record information, staff duty/role information in the project or task, staff weekly report text, and staff exchange record information in the process of the project or task.

Step S2, an emotional event is extracted from the original information. The method specifically comprises the following steps: calculating emotion basic index data related to the various types of original information based on the various types of original information; and obtaining corresponding emotional events according to preset rules and/or by adopting a trained machine learning model based on the emotional basic indexes. The emotion basic index data and the calculation method thereof are as described in the foregoing system, and are not described herein again. And after obtaining the emotion basic index data of the staff, obtaining a corresponding emotion event based on the emotion basic index data according to a certain preset rule. Events such as "divorce/marriage/wield/promotion/stand up/award/relatives/deaths/illness/parental dissimilarity". For some emotional events, which are predicted according to a trained machine learning model, for example, "workload is too large/staff interpersonal relationship is complex/boss requirement is harsh/fluctuation of emotion is large/co-workers are not good/work transition time is urgent/influence on decision making is absent/undefined role is stipulated/excessive rule regulations/unpleasant environment/new job challenge/new leadership adaptation/lack of interpersonal communication" or the like, model training can be performed according to already collected data, and then the currently collected data is evaluated by using the trained model to determine whether the emotional event can be obtained.

And step S3, processing the extracted emotion events according to the configured processing strategy to obtain the emotion index data of the employee. As shown in fig. 11, the method specifically includes the following steps:

and step S31, counting the number/frequency or severity of the emotional events occurring within the counting period based on the obtained emotional events, such as the data shown in the first table.

Step S32, a classification table is queried based on the extracted emotional events, and classification data of the emotional events is obtained. The nature and intensity values of the emotional events are recorded in the classification table, such as the data shown in the second table.

And step S33, calculating the emotion index data of the employee based on the classification data and the statistical data of the emotional event. In this step, the emotion index data of the employee may be calculated in the following manner:

an emotional coefficient p that measures the emotional impact of a single statistical period emotional event on the employee is calculated by the following equations 1-2:

wherein, the N is_iIs the property value, F, of the ith emotional event_iIs the frequency value of the occurrence of the ith emotional event, S_iAnd I is the intensity value of the ith emotional event, and the total number of emotional events in one statistical period is I.

And after the property value, the frequency value and the intensity value of each emotional event are multiplied, summing the products of the emotional events to obtain an emotional coefficient p of the current statistical period of the staff.

In another embodiment, the cumulative mood coefficient P may also be calculated for a plurality of statistical periods, for example: calculating the accumulated effect amount of the emotional events of the employee in the last four statistical periods (for example, each statistical period is one month) to obtain an accumulated emotional coefficient P, wherein the weight of the emotional event related value in the current month is the largest and is set to be a value 1, the weight of the emotional event related value in the last month is reduced to 0.7, the weight of the emotional event related value in the last two months is reduced to 0.4, and the weight of the emotional event related value in the last three months is reduced to 0.1, and a specific calculation formula is shown in formulas 1 to 3:

in other embodiments, each emotional event is used as a one-dimensional feature, and the emotional coefficient p of each emotional event is used_i＝N_iF_iS_iAnd obtaining a prediction sample as a characteristic value, inputting the prediction sample into a trained machine learning model, and evaluating the emotion of the employee through the machine learning model, wherein the output of the machine learning model is used as emotion index data. Specifically, the emotional coefficient p of each emotional event is calculated according to equation 1-1_i；

p_i＝N_iF_iS_iFormula 1-1

Then characterized by the emotional event, the emotional coefficient p of said emotional event_iAll emotional events of the employee are combined as feature values to get a prediction sample.

And then inputting the prediction sample into a machine learning model to obtain emotion index data of the target employee in a statistical period. Of course, the emotional coefficients of the accumulated statistical periods can be obtained by continuously using the formulas 1 to 3. For details, reference may be made to the description in the foregoing system, and details are not described herein.

And step S4, obtaining follow-up suggestions applied to the employees according to preset application conditions based on the emotion index data. In this step, emotional profile data of an employee is obtained by combining together an emotional event, emotional index data, and/or emotional base index data of the employee. And meanwhile, analyzing emotion portrait data of the employee based on application conditions, reading a corresponding follow-up advice information template from an advice information template library when the emotion portrait data of the employee meets the application conditions, and modifying the corresponding follow-up advice information template according to the emotion portrait data of the current employee to obtain a specific follow-up advice corresponding to the employee.

In a further aspect, a step S5 of graphically representing the employee' S mood profile data and/or specific follow-up advice is included. Namely, according to the set display requirements, the emotion image data of the employee is processed into corresponding graphical data and displayed in a display interface. When the emotion portrait data of an employee is displayed, the emotion portrait data and corresponding follow-up suggestions can be included.

The acquisition of information in step S1, the extraction of emotion events in step S2, and the calculation of emotion index data in step S3 may be different periods. For example, the partial information in step S1 is not repeatedly acquired after being acquired once, such as partial personal information. Some information needs to be updated regularly, such as marriage information, home address, performance score, compensation welfare and the like. The update period of these regularly updated information also varies, such as the performance score is the same as the calculation period of the performance score in the human resources system, such as monthly, quarterly, or half/year, while the compensation welfare is typically one or half year. And some information is acquired in real time, such as behavior information of employees. The extraction of emotional events may be daily or weekly or at the time of calculating the emotional index data. The final emotion index data of the employee may be calculated every week or every month, or may be calculated every day, and may be specifically set by a special person such as a manager.

In order to intervene timely when the emotion of the employee changes greatly or needs to intervene, in another embodiment, the present invention further includes a step S6 of monitoring the emotion of the employee. The method specifically comprises monitoring of emotion index data of some specific employees, monitoring of basic emotion index data of final emotions of the employees and monitoring of certain specific emotional events. For example: for monitoring certain specific emotion index data, such as ' card punching mood ' identified from facial expressions in daily attendance data, absence days ' based on the attendance data, and the like, when the index data are greater than or equal to corresponding threshold values, a reminding message is sent to related personnel.

For monitoring certain specific emotional events, such as 'death' and 'serious diseases', once the events occur, a reminding message is generated to the related personnel.

For the employee emotion index data obtained in step S3, for example, a reminder message is generated when the cumulative emotion coefficient P is a negative value and the absolute value thereof is larger than a certain value, or a reminder message is generated to the relevant person when an extremely negative emotion category is obtained by machine learning model evaluation. Thus allowing timely intervention when the employee generates a negative or significant emotional event.

The system provided by the invention can be used as a supplement of the existing human resource system in an enterprise, is separated from the existing human resource system during implementation, is connected with the existing human resource system through an interface, and can also be made into a system. As shown in fig. 12, the emotion information processing system 200 provided by the present invention is connected to the enterprise system 100 through an interface, and both share a low privilege interface 301, a high privilege interface 302, and a comprehensive database 400. The enterprise system 100 includes, for example, a human resources management system, some specialty systems. As general staff, such as interviewers, attendance recording staff, training lecturers, general human resource specialists, general managers, general mental health specialists, and the like, use the enterprise system 100 and the emotion information processing system 200 through the low-privilege interface 301, and as such, record various kinds of raw data, such as attendance information, training information, interview feedback information, observation information, and the like, through the enterprise system 100. The enterprise system 100 processes and processes a part of the original data according to the set function to obtain corresponding primary information, such as interview result records, attendance records, performance scores, salaries and benefits, task allocation of employees, post roles, and the like, and stores the primary information in the comprehensive database 400. Managers and mental health professionals with high use authority can view the enterprise system 100 and the emotion information processing system 200 through the high authority interface 302, and the emotion information processing system 200 can display emotion index data, emotion image data and corresponding follow-up suggestions of the employees through the high authority interface 302. The related management personnel can comprehensively know the emotion of the staff, the root of emotion generation, advice for improving emotion and the like through the personal emotion portrait of the staff, and enterprises can effectively manage the emotion of the staff.

Fig. 13 is a schematic diagram of the structural connection of an emotion information processing system according to an embodiment of application of the present invention. In the present invention, the emotion information processing system includes a server and terminals, where the terminals may be a computer 10c and a personal terminal 11c, and the server is, for example, one or more servers 2 c. The server side is connected with the terminal through a network, and the computers 10c can be connected through an internal network. Various modules of the emotion information processing system may be distributed among different servers 2c, computer hosts 10c, and personal terminals 11 c. The server side also comprises a database 3c for storing various information and data as an emotion database or with an enterprise database.

With the market competition and the change of technical innovation faced by enterprises, more and more work needs to be completed in a team mode. According to research, individuals with different emotion processing capabilities (also called emotional intelligence) as a component unit of a team determine the emotional intelligence of the team existing as the state of the team and the work performance of the team, and further influence the competitiveness and performance of the whole enterprise. As shown by the existing research, even if the short-term positive interaction relationship between the enterprise employees and the employees can also have quantitative positive influence on the working attitude, the learning behavior and the physiological and psychological health of the employees, so that the overall performance and competitiveness of the enterprise or organization are improved. The invention can analyze the emotion state of the staff and generate specific suggestions for improving and adjusting the emotion and the like of the staff through various collected public information related to emotion, such as personal information stored in a human resource system, interpersonal information obtained from geographical positions and work, feedback information of other people, public personal behavior information expressed by the staff in a workplace and the like, thereby fully exerting the potential of the staff and improving the emotional intelligence of the individuals and the teams by improving the emotion of the staff, and further improving the overall competitiveness and the performance of enterprises.

The above embodiments are provided only for illustrating the present invention and not for limiting the present invention, and those skilled in the art can make various changes and modifications without departing from the scope of the present invention, and therefore, all equivalent technical solutions should fall within the scope of the present invention.

Claims

1. An emotion information processing system comprising:

the system comprises an information collection module, a data processing module and a data processing module, wherein the information collection module is configured to acquire original information related to the emotion of an employee according to the personal identity of the employee;

an emotional event extraction module, connected to the information collection module, configured to extract emotional events from the original information;

the emotion index acquisition module is connected with the emotion event extraction module and is configured to process the extracted emotion events according to a configured processing strategy so as to obtain emotion index data of the staff; and

an application module, connected to the emotion indicator acquisition module, configured to obtain follow-up advice applied to the employee in accordance with a preset application condition based on the emotion indicator data.

2. The system of claim 1, wherein the information collection module comprises one or more of the following:

a personal information collection unit configured to collect personal information of the employee, the personal information including one or more of personal identity information, attendance information, performance information, training information, compensation welfare information;

the interpersonal information collection unit is configured to collect interpersonal interaction information of the staff;

one or more feedback units configured to at least receive interview/observation feedback information input by a particular person;

one or more behavior information acquisition units configured to acquire public behavior information of the employee at the workplace; wherein, the public behavior information is the times/frequency of specific daily behaviors of the staff.

3. The system of claim 2, wherein the information collection module further comprises a conversion unit configured to convert non-textual information in the original information into textual information.

4. The system of claim 2, wherein the interpersonal information collection unit comprises:

a geographical location information collecting subunit configured to collect geographical location information of the employee, the geographical location information including at least location layout information of the employee's workplace; and

the task information collecting subunit is configured to collect the work information participated by the staff, wherein the work information comprises one or more of project and/or task basic information participated by the staff, project and/or task progress record information, the duty/role information of the staff in the project or task, staff weekly report text, and personnel exchange record information in the process of the project or task progress.

5. The system of claim 1, wherein the emotional event extraction module further comprises:

the emotion basic index calculation unit is configured to calculate emotion basic index data related to various types of original information based on the original information; and

an emotional event evaluation unit, connected to the emotional base indicator calculation unit, configured to evaluate the emotional base indicator to obtain an emotional event.

6. The system according to claim 5, wherein the emotional event evaluation unit obtains emotional events according to preset rules and/or using a trained machine learning model.

7. The system of claim 1, 5 or 6, wherein the mood indicator obtaining module further comprises:

an emotional event statistics unit configured to count a number/frequency of occurrences of the emotional event within a statistics period, and/or a severity value based on the derived emotional event;

a classification unit configured to query a classification table based on the extracted emotional events, thereby obtaining classification data of the emotional events; and

a calculating unit connected with the classifying unit and configured to calculate emotional index data of the employee based on the classified data and the statistical data of the emotional event.

8. The system of claim 7, wherein the computing unit further comprises:

a feature value calculation operator unit configured to calculate an emotional coefficient p of each emotional event according to formula 1-1 based on the classification data and the statistical data of the emotional events_i；

p_i＝N_iF_iS_iEquation 1-1

Wherein, the N is_iIs the property value, F, of the ith emotional event_iIs the frequency value of the occurrence of the ith emotional event, S_iIntensity value for the ith emotional event;

a sample generation subunit, configured to use an emotional event as a feature, and combine all emotional events of the employee with an emotional coefficient of the emotional event as a feature value to obtain a prediction sample; and

a prediction subunit configured to input prediction samples to a machine learning model to derive emotional index data for the target employee over a statistical period.

9. The system of claim 7, wherein the computing unit further comprises:

the emotion coefficient calculation unit is configured to calculate an emotion coefficient p of the target employee in a statistical period according to a formula 1-2 based on the classification data and the statistical data of the emotional event;

wherein, the N is_iIs the property value, F, of the ith emotional event_iIs the frequency value of the occurrence of the ith emotional event, S_iThe intensity value of the ith emotional event is shown, and I is the total number of emotional events in a statistical period; and

and the cumulative emotion coefficient calculation unit is connected with the emotion coefficient calculation unit and is configured to calculate weighted sums of emotion coefficients of a plurality of statistical periods, the weighted sums of the emotion coefficients of the statistical periods are used as emotion index data, and the weights for calculating the weighted sums of the emotion coefficients are sequentially reduced according to the time distance from the current statistical period.

10. The system of claim 1, wherein the application module comprises:

an employee emotion portrayal unit configured to obtain emotion portrayal data of an employee based on an emotion event, emotion indicator data and/or emotion base indicator data of the employee; and

and the follow-up suggestion generation unit is configured to generate corresponding follow-up suggestions according to the emotion portrait data of the staff based on the application conditions and the corresponding processing strategies.

11. The system of claim 10, further comprising a suggestion template library configured to provide follow-up suggestion templates corresponding to various application conditions; correspondingly, the follow-up suggestion generation unit determines a corresponding application information template according to application conditions met by the employee emotion portrait data, emotion index data and/or emotion basic index data, and modifies corresponding data in the application information template based on the emotion employee portrait data, emotion index data and/or emotion basic index data to generate the follow-up suggestion.

12. The system of claim 10, further comprising a display module configured to process the emotional employee representation data and/or follow-up advice into corresponding graphics or charts for display or output in accordance with preset visualization requirements.

13. The system according to claim 1, further comprising a reminding module, connected to the emotional event extraction module and/or the application module, configured to process the extracted emotional event or the emotional basic indicator data and/or the emotional indicator data, and send out a reminding message when the reminding condition is met.

14. An emotion information processing method, comprising:

acquiring original information related to the emotion of the employee according to the personal identity of the target employee;

extracting emotional events from the original information;

processing the extracted emotional events according to a configured processing strategy to obtain emotional index data of the employees; and

and obtaining follow-up suggestions applied to the staff according to preset application conditions based on the emotion index data.

15. The method of claim 14, wherein the raw information related to the emotion of the employee comprises one or more of personal information of the employee, interpersonal interaction information, interview/observation feedback information for a particular person, and public behavioral information of the employee at the workplace.

16. The method of claim 15, wherein the employee personal information includes one or more of personal identification information, attendance information, performance information, training information, compensation welfare information.

17. The method of claim 15, wherein the interpersonal interaction information includes geographical location information and/or work information engaged by employees.

18. The method of claim 17, wherein the geographic location information includes at least location layout information of employee work sites; the work information comprises one or more of project and/or task basic information participated by the staff, project and/or task progress record information, staff duty/role information in the project or task, staff weekly report text, and staff exchange record information in the process of the project or task.

19. The method of claim 14, wherein extracting emotional events from the raw information comprises:

calculating emotion basic index data related to the various types of original information based on the various types of original information; and

and obtaining corresponding emotional events according to preset rules and/or by adopting a trained machine learning model based on the emotional basic indexes.

20. The method of claim 19, wherein the step of obtaining mood indicator data for the employee further comprises:

counting the number/frequency or severity value of the emotional events occurring in a counting period based on the obtained emotional events;

inquiring a classification table based on the extracted emotional events, and further obtaining classification data of the emotional events; and

calculating emotional index data of the employee based on the classification data and the statistical data of the emotional event.

21. The method of claim 20, wherein the step of calculating the employee emotion metric data further comprises:

categorical data and statistical data according to formula based on emotional events1-1 calculating the emotional coefficient p for each emotional event_i；

p_i＝N_iF_iS_iFormula 1-1

Wherein, the N is_iIs the property value, F, of the ith emotional event_iIs the frequency value of the occurrence of the ith emotional event, S_iAn intensity value for the ith emotional event;

combining all emotional events of the employees by taking the emotional events as features and taking the emotion coefficients of the emotional events as feature values to obtain a prediction sample; and

and inputting the prediction samples into a machine learning model to obtain emotion index data of the target employee in a statistical period.

22. The method of claim 20, wherein the step of calculating the employee emotion metric data further comprises:

calculating an emotion coefficient p of the target employee in a statistical period according to a formula 1-2 based on the classification data and the statistical data of the emotional event;

and calculating weighted sums of the emotion coefficients of a plurality of statistical periods, and taking the weighted sums of the emotion coefficients of the statistical periods as emotion index data, wherein the weights for calculating the weighted sums of the emotion coefficients are sequentially reduced according to the time distance from the current statistical period.

23. The method of claim 14, further comprising: and obtaining the emotion portrait of the employee based on the emotion index data, the emotion events and the emotion basic index data of the employee.

24. The method of claim 20, further comprising:

judging whether the reminding condition is met or not when obtaining the emotion basic index data and/or the emotion event and/or the emotion index data; and

and sending out a reminding message in response to the emotion basic index data and/or the emotion event and/or the emotion index data meeting the reminding condition.