CN109872026A - Evaluation result generation method, device, equipment and computer readable storage medium - Google Patents
Evaluation result generation method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN109872026A CN109872026A CN201811534540.2A CN201811534540A CN109872026A CN 109872026 A CN109872026 A CN 109872026A CN 201811534540 A CN201811534540 A CN 201811534540A CN 109872026 A CN109872026 A CN 109872026A
- Authority
- CN
- China
- Prior art keywords
- preset number
- score
- expression
- answer
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of evaluation result generation method, device, equipment and computer readable storage mediums, it is related to financial air control systems technology field, so that the evaluation result generated not only allows for the answer of the problem of user's input, user is also contemplated in expression when evaluating and testing topic of answering, the true idea that evaluation result is more close to the users, measures are more diversified, and obtained evaluation result accuracy is higher.The described method includes: extracting expression data when user inputs problem answers in image data when instruction is submitted in the answer for receiving user;Corresponding first score of expression data is obtained respectively, is calculated the summation of the first score, is obtained expression score;Corresponding second score of problem answers is obtained respectively, is calculated the summation of the second score, is obtained answer score;Using Weight algorithm, expression score and answer score are calculated, generate evaluation result.
Description
Technical field
The present invention relates to financial air control systems technology fields, more particularly to a kind of evaluation result generation method, device, set
Standby and computer readable storage medium.
Background technique
As the improvement of people's living standards, and Internet technology maturation, while pushing expanding economy, also
Promote the innovation of finance.The product that internet finance is combined as finance and science and technology, plays more next in daily life
More important role.User can realize the various operations such as account management, online payment, purchase financial product by internet.
Wherein, some financial products usually have certain requirement to the risk tolerance of buyer, therefore, in financial institution to user
Before selling these financial products, risk assessment operation can be carried out to user using financial air control systems technology, generate user's
Evaluation result is with for reference.
In the related technology, when carrying out risk assessment operation to user, the usually assessment of answer form, namely in terminal
On to user show multiple tracks topic, the answer of per pass topic is provided by user, and assessed according to these answers, to generate
The evaluation result of the user.
In the implementation of the present invention, inventor find the relevant technologies the prior art has at least the following problems:
The evaluation result that the risk assessment of answer form generates can only record the answer of user's selection, cannot be distinguished from user and do
Whether the answer selected when topic is the true idea of user, and measures are relatively simple, obtained evaluation result accuracy compared with
It is low.
Summary of the invention
In view of this, the present invention provides a kind of evaluation result generation method, device, equipment and computer-readable storage mediums
Matter, main purpose are to solve to cannot be distinguished from whether the answer selected when user inscribes is the true idea of user at present, survey
Comment mode relatively simple, the lower problem of obtained evaluation result accuracy.
According to the present invention in a first aspect, providing a kind of evaluation result generation method, this method comprises:
When instruction is submitted in the answer for receiving user, the user is extracted in image data and inputs asking for preset number
Preset number expression data when answer is inscribed, described image data are the user the problem of inputting preset number when answer
The image data acquired respectively;
The preset number expression data the first score of corresponding preset number is obtained respectively, calculates the present count
The summation of the first score of mesh, obtains expression score;
The problem of obtaining the preset number respectively answer the second score of corresponding preset number, calculates the present count
The summation of the second score of mesh, obtains answer score;
Using Weight algorithm, the expression score and the answer score are calculated, generate evaluation result.
Second aspect according to the present invention, provides a kind of evaluation result generating means, which includes:
Extraction module, for it is defeated to extract the user in image data when instruction is submitted in the answer for receiving user
Preset number expression data when the problem of enter'sing preset number answer, described image data are that the user answers in input problem
The image data acquired when case;
First computing module, for obtaining corresponding first point of the preset number of the preset number expression data respectively
Number calculates the summation of the first score of the preset number, obtains expression score;
Second computing module, answer corresponding second point of preset number the problem of for obtaining the preset number respectively
Number calculates the summation of the second score of the preset number, obtains answer score;
Generation module calculates the expression score and the answer score, generation is commented for using Weight algorithm
Survey result.
The third aspect according to the present invention, provides a kind of equipment, including memory and processor, and the memory is stored with
The step of computer program, the processor realizes above-mentioned first aspect the method when executing the computer program.
Fourth aspect according to the present invention provides a kind of computer readable storage medium, is stored thereon with computer program,
The computer program realizes the step of method described in above-mentioned first aspect when being executed by processor.
By above-mentioned technical proposal, a kind of evaluation result generation method, device, equipment and computer provided by the invention can
Storage medium is read, compared with the mode for the evaluation result that the assessment of the risk of current answer form generates, the present invention, which works as, receives use
When instruction is submitted in the answer at family, preset number table when the problem of user inputs preset number answer is extracted in image data
Feelings data, and obtain preset number expression data the first score of corresponding preset number respectively calculate preset number a the
The problem of summation of one score obtains expression score, obtains preset number respectively answer the second score of corresponding preset number,
The summation for calculating preset number the second score, obtains answer score, using Weight algorithm, to expression score and answer score into
Row calculates, and generates evaluation result, so that the problem of evaluation result generated not only allows for user's input answer, it is also contemplated that use
Family is in expression when evaluating and testing topic of answering, and the true idea that evaluation result is more close to the users, measures are more diversified, obtain
The evaluation result accuracy arrived is higher.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 shows a kind of evaluation result generation method flow diagram provided in an embodiment of the present invention;
Fig. 2 shows a kind of evaluation result generation method flow diagrams provided in an embodiment of the present invention;
Fig. 3 A shows a kind of structural schematic diagram of evaluation result generating means provided in an embodiment of the present invention;
Fig. 3 B shows a kind of structural schematic diagram of evaluation result generating means provided in an embodiment of the present invention;
Fig. 3 C shows a kind of structural schematic diagram of evaluation result generating means provided in an embodiment of the present invention;
Fig. 3 D shows a kind of structural schematic diagram of evaluation result generating means provided in an embodiment of the present invention;
Fig. 3 E shows a kind of structural schematic diagram of evaluation result generating means provided in an embodiment of the present invention;
Fig. 4 shows a kind of structural schematic diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
The embodiment of the invention provides a kind of evaluation result generation methods, can achieve true when being more close to the users answer
Real idea, measures diversification, the obtained higher purpose of evaluation result accuracy, as shown in Figure 1, this method comprises:
101, when instruction is submitted in the answer for receiving user, user is extracted in image data and inputs asking for preset number
Preset number expression data when answer is inscribed, image data is that user acquires when answer respectively the problem of inputting preset number
Image data.
In embodiments of the present invention, when instruction is submitted in the answer for receiving user, it is defeated that user is extracted in image data
Before preset number expression data when the problem of enter'sing preset number answer, it is also necessary to be asked in the risk evaluation and test for receiving user
When asking, the evaluation and test topic of preset number is transmitted to user, starting acquisition equipment acquires image data based on acquisition equipment.
Firstly, when receive answer submit instruction when, respectively determine preset number the problem of answer input time section, obtain
To the input time section of preset number.Specifically, when receiving answer submission instruction, user is obtained in input preset number
The consuming time of problem answers will expend time and image data mapping on a timeline;According to receiving asking for preset number
The time of answer is inscribed, consuming time and image data are divided on a timeline, obtain the fragment data of preset number.
Then, the problem of obtaining image data, determining preset number respectively answer corresponding present count in image data
Target fragment data determine the image scaled of image data, acquisition and the matched multiple sample expressions of image scaled, for default
Each fragment data in the fragment data of number calculates multiple similarities between fragment data and multiple sample expressions.Tool
Body, for each fragment data in the fragment data of preset number, coordinate is established for fragment data and multiple sample expressions
System;For each sample expression in multiple sample expressions, target numbers are extracted in fragment data and sample expression respectively
First object point and target numbers the second target point.Count the first object point of target numbers and the second mesh of target numbers
The number for the target point being overlapped in punctuate, using number as the similarity between fragment data and sample expression.By repeating to hold
The process of similarity between the above-mentioned determining fragment data of row and sample expression, determines between fragment data and multiple sample expressions
Multiple similarities.
Finally, multiple similarities are ranked up from big to small, the sample expression of the similarity instruction to rank the first is extracted
Expression data as fragment data.By repeating the similarity between above-mentioned calculating fragment data and multiple sample expressions
Process, obtain the corresponding preset number expression data of fragment data of preset number.
102, preset number expression data the first score of corresponding preset number is obtained respectively, calculates preset number
The summation of first score obtains expression score.
In embodiments of the present invention, after the expression data of the preset number of fragment data of preset number has been determined, just
The first score of the available corresponding preset number of preset number expression data, calculates the total of the first score of preset number
With to obtain expression score.
103, the problem of obtaining preset number respectively answer the second score of corresponding preset number, calculates preset number
The summation of second score obtains answer score.
In embodiments of the present invention, asking for preset number can be obtained after answer when preset number has been determined the problem of
Answer the second score of corresponding preset number is inscribed, the summation of the second score of preset number is calculated, to obtain answer score.
104, using Weight algorithm, expression score and answer score are calculated, generate evaluation result.
In embodiments of the present invention, when generating evaluation result, firstly, determining the of expression score and answer score respectively
One weight and the second weight;Then, using Weight algorithm, the first product of computational chart mutual affection number and the first weight calculates answer
Second product of score and the second weight;Finally, the sum of products of the first product and the second product is calculated, using sum of products as evaluation and test
As a result.
It, can also be according to the expression data of user, to user's in order to keep the risk assessment carried out to user more accurate
Personality is predicted, generates personality prediction result, personality prediction result and evaluation result are returned together.Specifically, it is generating
When personality prediction result, firstly, the frequency of occurrences of each expression data in preset number expression data is counted, by the frequency of occurrences
It is ranked up from big to small;Then, the corresponding target expression data of the frequency of occurrences to rank the first is obtained, inquires and determines object table
The corresponding target personality of feelings data, using target personality as the personality prediction result of user;Finally, evaluation result and personality is pre-
If result returns.
Method provided in an embodiment of the present invention is extracted in image data when instruction is submitted in the answer for receiving user
User inputs the preset number expression data when answer of the problem of preset number, and obtains preset number expression data respectively
The first score of corresponding preset number, calculates the summation of the first score of preset number, obtains expression score, obtains respectively pre-
If the problem of number answer the second score of corresponding preset number, calculates the summation of the second score of preset number, is answered
Case score calculates expression score and answer score using Weight algorithm, generates evaluation result, so that the evaluation and test generated
As a result the problem of not only allowing for user's input answer, it is also contemplated that user is in expression when evaluating and testing topic of answering, evaluation result
The true idea being more close to the users, measures are more diversified, and obtained evaluation result accuracy is higher.
The embodiment of the invention provides a kind of evaluation result generation methods, can achieve true when being more close to the users answer
Real idea, measures diversification, the obtained higher purpose of evaluation result accuracy, as shown in Fig. 2, this method is applied to eventually
In end, this method comprises:
201, in the risk evaluation and test request for receiving user, the evaluation and test topic of preset number is transmitted to user, and open
Dynamic acquisition equipment acquires image data based on acquisition equipment.
In embodiments of the present invention, general risk evaluation and test would generally provide default problem for user, by user to asking
Topic answer, answer the problem of problem is supplied to financial institution, so as to financial institution and problem answer be user into
The evaluation and test of row risk.And user is in answer to a question, may select sometimes for the true idea for covering up heart in some violate
The problem of heart answer, in this way, subsequent the problem of being submitted according to user answer will be with the reality of user if carrying out risk evaluation and test
Situation is not inconsistent, and accuracy is not high.It was recognized by the inventor that user is the problem of heart is violated in selection when answer, it will usually show
It hesitates out, is uneasy or irritable, and these performances different degrees of can be embodied in the facial expression of user, therefore, in user
When carrying out answer, the image data of the face of user can be acquired, and in the subsequent progress risk evaluation and test to the user, by user
Face expression data also take into account, so as to improve generation evaluation result accuracy.
Wherein, financial institution can be provided as user and carry out the client of risk evaluation and test, and provide risk in the client
Entrance is evaluated and tested, when detecting that user triggers risk evaluation and test entrance, determines the risk evaluation and test request for receiving user, it will
The evaluation and test topic of ready preset number is transferred to user, so that user answers to evaluation and test topic, thus after answering
The problem of answer submit.During practical application, the number and particular content for evaluating and testing topic can be by financial institutions certainly
Row determines that the embodiment of the present invention is to this without specifically limiting.In order to completely record table of the user when carrying out risk evaluation and test
End of love, in the risk evaluation and test request for receiving user, just starting acquisition equipment, acquires user based on the acquisition equipment and is answering
Image data when topic.During practical application, acquisition equipment can hold terminal by external equipment or user
Acquisition module, for example, monitoring camera, cell-phone camera head etc., the embodiment of the present invention is specially any equipment to acquisition equipment
And device which position without limit.
202, when receiving answer submission instruction, acquisition user is the problem of inputting preset number when the consuming of answer
Between, time and image data mapping will be expended on a timeline, according to the time of answer the problem of receiving preset number, when
Between on axis to the time is expended and image data divides, obtain the fragment data of preset number.
It in embodiments of the present invention, is to input one by one over time when inputting problem answers due to user
, therefore, when receiving answer submission instruction, determine that user has completed answering to whole evaluation and test topics, at this moment, just
It can determine that user inputs the input time of each problem answers.Specifically, performance user for clarity inputs each
Relationship between problem answers and time, it is possible, firstly, to the consuming time of user's answer the problem of inputting preset number is obtained,
And correspondence mappings are on a timeline simultaneously by the consuming time and image data;Subsequently, for each problem answers, determining should
A upper problem answers for problem answers complete the first time of input and the problem answers complete the second time inputted,
Using the difference of first time and the second time as the time for receiving the problem answers.It is received often in this way, can determine
The time of one problem answers, respectively according to the problem of receiving preset number in answer each problem answers time, by
Time shaft divides consuming time and image data, the period that each problem answers are entered is generated, to obtain pre-
If the fragment data of number.
203, it determines the image scaled of image data, obtains and preset with the matched multiple sample expressions of image scaled, calculating
The similarity of the fragment data of number and multiple sample expressions, determines preset number expression data.
In embodiments of the present invention, the segments when getting user in image data and inputting each problem answers
According to rear, in order to determine that expression of the user when inputting each problem answers is specially any expression, multiple samples can be set
This expression, and the similarity between each fragment data and sample expression is calculated, thus will be with fragment data similarity highest
Expression data of the sample expression as fragment data, so that it is determined that the preset number expression number of the fragment data of preset number
According to.
Wherein, it is contemplated that acquisition equipment is different from different the distance between users, so that acquired image number
According to size be different namely the ratio of acquired image data there are many, in order to guarantee that identification to fragment data is quasi-
Really, the identification mistake for avoiding occurring fragment data, when obtaining multiple sample expressions, it is necessary first to determine the image of image data
Ratio;Then, it obtains and the matched multiple sample expressions of image scaled;Finally, calculate preset number fragment data with it is multiple
The similarity of sample expression, so that it is determined that preset number expression data.It is default being determined according to the fragment data of preset number
It, can be by executing following steps for each of the fragment data of preset number fragment data when number expression data
Rapid one process into step 3 is realized.
Step 1: coordinate system is established for fragment data and multiple sample expressions, for each sample in multiple sample expressions
This expression extracts the first object point of target numbers and the second mesh of target numbers in fragment data and sample expression respectively
Punctuate.
For each sample expression in multiple sample expressions, in order to which determine fragment data and the sample expression is overlapped journey
How many is spent, can be first fragment data and sample expression using the point of same position as origin, establish identical right angle and sit
Mark system.Then, equal number of first object point and the second target point are extracted in fragment data and sample expression, so as to
The subsequent similarity determined based on first object point and the second target point between fragment data and sample expression.
Wherein, when extracting first object point and the second target point, target numbers can be set, and respectively in fragment data
It is middle extract target numbers first object point, and in sample expression extract target data the second target point.Extracting the
When one target point and the second target point, need the first object point for guaranteeing to extract and the second target point that can sketch the contours of user and exist
Facial expression in fragment data, guarantee can identify fragment data.
Step 2: the target point being overlapped in the first object point of statistics target numbers and the second target point of target numbers
Number, using number as the similarity between fragment data and sample expression.
Since if fragment data were more similar to the sample expression, the of the first object point of fragment data and sample expression
Two target points are overlapped more, therefore, can be by counting the first object point of target numbers and the second mesh of target numbers
The target point number being overlapped in punctuate, to determine the similarity between fragment data and sample expression.Wherein, similarity is being determined
When, it can also be calculated directly using the number for the target point being overlapped in first object point and the second target point as similarity
The number of the target point of coincidence ratio shared in target numbers, using the ratio as similarity.The embodiment of the present invention is to life
At the method for the similarity between fragment data and sample expression without specifically limiting.
By repeating the process of the similarity between above-mentioned determining fragment data and sample expression, this can be determined
Multiple similarities in fragment data and multiple sample expressions between each sample expression.
Step 3: multiple similarities are ranked up from big to small, the sample table of the similarity instruction to rank the first is extracted
Expression data of the feelings as fragment data.
After generating multiple similarities of the fragment data and multiple sample expressions, due to the higher expression segment of similarity
Data and sample expression are closer, and therefore, multiple similarities are ranked up from big to small, and extract the similarity to rank the first
Expression data of the sample expression of instruction as the fragment data, the sample expression for also indicating highest similarity is as this
The expression data of fragment data.During practical application, multiple similarities can also be ranked up from small to large, and will
Come expression data of the sample expression of the similarity instruction of last bit as the fragment data.
By repeating above-mentioned steps one between calculating fragment data and multiple sample expressions shown in step 3
Similarity process, the corresponding preset number expression data of fragment data of preset number can be got, so as to
It is subsequent to be assessed according to preset number expression data, thus when generating evaluation result by user when inputting answer
Expression data also comprehensively consider.
204, the first score of each corresponding preset number of expression data in preset number expression data is obtained respectively,
The summation for calculating the first score of preset number, obtains expression score.
In embodiments of the present invention, after the fragment data according to preset number has determined preset number expression data,
Corresponding first score of each expression data in preset number expression data can be obtained respectively, get preset number
First score obtains expression score to calculate the summation of the first score of preset number.
Wherein, it is contemplated that the type that the attribute different to user carries out the evaluation and test topic being related to when risk assessment is different
, user's activity of heart when answering different types of evaluation and test topic may also be different, therefore, for different types of
Topic is evaluated and tested, the first different score lists can be set, to inquire each expression data pair in the first score list
The first score answered, to obtain expression score.During practical application, the first score list of setting can specifically be joined
See below table 1.
Table 1
Expression data | First score |
It smiles | 5 points |
It is tranquil | 3 points |
It frowns | - 2 points |
… | … |
After each expression data corresponding first score has been determined, the first score of preset number can be obtained.
By calculating the summation of the first score of preset number, expression score of the user when carrying out evaluation and test topic and answering is produced.
For example, setting according to the first score that 5 expression datas of user determine is respectively " 5 points ", " 3 points ", " 3 points ", " 3 points " and " 5
Point ", then the expression score obtained is 5+3+3+3+5=19 points.
205, the second score of each corresponding preset number of problem answers in the problem of obtaining preset number respectively answer,
The summation for calculating the second score of preset number, obtains answer score.
In embodiments of the present invention, after generating the expression score of user, based on the problem of user inputs answer
The basis that risk evaluation and test is carried out to user, each problem answers in answer the problem of therefore, it is necessary to obtain preset number respectively
Corresponding second score obtains the second score of preset number, the summation of the second score of preset number is calculated, to be answered
Case score.
Wherein, it is contemplated that the type that the attribute different to user carries out the evaluation and test topic being related to when risk assessment is different
, the score of the different options of different types of evaluation and test topic may be different, and therefore, be inscribed for different types of evaluation and test
The second different score lists can be set in mesh, to inquire each problem answers corresponding in the second score list
Two scores, to obtain answer score.During practical application, the second score list of setting specifically may refer to following
Table 2.
Table 2
After each problem answers corresponding second score has been determined, the second score of preset number can be obtained.
By calculating the summation of the second score of preset number, answer score of the user when carrying out evaluation and test topic and answering is produced.
For example, setting according to the second score that 5 problem answers of user determine is respectively " 5 points ", " 3 points ", " 3 points ", " 3 points " and " 5
Point ", then the answer score obtained is 5+3+3+3+5=19 points.
206, the first weight and the second weight for determining expression score and answer score respectively are calculated using Weight algorithm
First product of expression score and the first weight, calculate answer score and the second weight the second product, calculate the first product and
The sum of products of second product, using sum of products as evaluation result.
In embodiments of the present invention, after expression score and answer score has been determined, in order to comprehensively consider expression score and
Answer score generates evaluation result, can be set the weight of expression score and answer score, and then using Weight algorithm by table
Mutual affection number and answer combination of points, generate the evaluation result of the user.Specifically, firstly, determining expression score and answer respectively
The first weight and the second weight of score;Then, using Weight algorithm, the first product of computational chart mutual affection number and the first weight,
The second product of answer score and the second weight is calculated, the sum of products of the first product and the second product is calculated;Finally, will obtain
Evaluation result of the product as the user.
207, the frequency of occurrences of each expression data in preset number expression data is counted, from big to small by the frequency of occurrences
It is ranked up, obtains the corresponding target expression data of the frequency of occurrences to rank the first, inquire and determine that target expression data is corresponding
Evaluation result and personality default result using target personality as the personality prediction result of user, and are back to use by target personality
Family.
In embodiments of the present invention, due to user, the higher expression data of the frequency of occurrences has more representative during answering
Property, the personality of description user that can be rough therefore, can be with root in order to keep the risk evaluation and test carried out to user more accurate
According to the expression data of obtained preset number, the personality of user is predicted, generates the personality prediction result of the user, by property
Lattice prediction result and evaluation result return together, so that the comprehensive personality prediction result of staff is analyzed, guarantee to
The risk evaluation and test that family carries out is more accurate.
Wherein, when generating the personality prediction result of the user, firstly, each table in statistics preset number expression data
The frequency of occurrences is ranked up by the frequency of occurrences of feelings data from big to small, obtains the corresponding target of the frequency of occurrences to rank the first
Expression data;Then, it inquires and determines the corresponding target personality of target expression data;Finally, using target personality as the property of user
Lattice prediction result.During practical application, personality prediction table as shown in table 3 can be set, will pass through in personality
It is inquired in prediction table to predict the personality of user.
Table 3
Expression data | The frequency of occurrences | Predict personality |
It smiles | ≥10 | It is optimistic |
It is tranquil | ≥20 | It is sedate |
It frowns | ≥20 | Strictly |
… | … | … |
It should be noted that since the number for the evaluation and test topic being related in different scenes is different, needle
Different personality can be set to the different numbers of evaluation and test topic and predict table, guarantee that the personality carried out to user prediction is opposite
Accurately.
Method provided in an embodiment of the present invention is extracted in image data when instruction is submitted in the answer for receiving user
User inputs the preset number expression data when answer of the problem of preset number, and obtains preset number expression data respectively
The first score of corresponding preset number, calculates the summation of the first score of preset number, obtains expression score, obtains respectively pre-
If the problem of number answer the second score of corresponding preset number, calculates the summation of the second score of preset number, is answered
Case score calculates expression score and answer score using Weight algorithm, generates evaluation result, so that the evaluation and test generated
As a result the problem of not only allowing for user's input answer, it is also contemplated that user is in expression when evaluating and testing topic of answering, evaluation result
The true idea being more close to the users, measures are more diversified, and obtained evaluation result accuracy is higher.
Further, the specific implementation as Fig. 1 the method, the embodiment of the invention provides a kind of generations of evaluation result
Device, as shown in Figure 3A, device include: extraction module 301, the first computing module 302, the second computing module 303 and generation mould
Block 304.
The extraction module 301, for it is defeated to extract user in image data when instruction is submitted in the answer for receiving user
Preset number expression data when the problem of enter'sing preset number answer, image data are user the problem of inputting preset number
The image data acquired respectively when answer;
First computing module 302, for obtaining the corresponding preset number first of preset number expression data respectively
Score calculates the summation of the first score of preset number, obtains expression score;
Second computing module 303 is used for the corresponding preset number second of the problem of obtaining preset number respectively answer
Score calculates the summation of the second score of preset number, obtains answer score;
The generation module 304 calculates expression score and answer score, generates evaluation and test for using Weight algorithm
As a result.
In specific application scenarios, as shown in Figure 3B, which further includes transmission module 305 and acquisition module 306.
The transmission module 305, in the risk evaluation and test request for receiving user, the evaluation and test topic of preset number to be passed
Transport to user;
The acquisition module 306 acquires image data based on acquisition equipment for starting acquisition equipment.
In specific application scenarios, as shown in Figure 3 C, the extraction module 301, including determine submodule 3011, obtain son
Module 3012, computational submodule 3013 and extracting sub-module 3014.
The determination submodule 3011, for determining answered the problem of preset number respectively when receiving answer submission instruction
The fragment data of case corresponding preset number in image data;
The acquisition submodule 3012 obtains matched multiple with image scaled for determining the image scaled of image data
Sample expression;
The computational submodule 3013 calculates segment for each fragment data in the fragment data for preset number
Multiple similarities between data and multiple sample expressions;
The extracting sub-module 3014, for multiple similarities to be ranked up from big to small, extract rank the first it is similar
Spend expression data of the sample expression of instruction as fragment data;
The computational submodule 3013 is also used to repeat the phase between above-mentioned calculating fragment data and multiple sample expressions
Like the process of degree, the corresponding preset number expression data of fragment data of preset number is obtained.
In specific application scenarios, the determination submodule 3011, for obtaining and using when receiving answer submission instruction
The consuming time of family answer the problem of inputting preset number will expend time and image data mapping on a timeline;According to
The time of the problem of receiving preset number answer on a timeline divides consuming time and image data, obtains pre-
If the fragment data of number.
In specific application scenarios, the computational submodule 3014, for every in the fragment data for preset number
A fragment data establishes coordinate system for fragment data and multiple sample expressions;For each sample table in multiple sample expressions
Feelings extract the first object point of target numbers and the second target of target numbers in fragment data and sample expression respectively
Point;The number for counting the target point being overlapped in the first object point of target numbers and the second target point of target numbers, by number
As the similarity between fragment data and sample expression;Repeat the phase between above-mentioned determining fragment data and sample expression
Like the process of degree, multiple similarities between fragment data and multiple sample expressions are determined.
In specific application scenarios, as shown in Figure 3D, the generation module 304, including determine submodule 3041, the first meter
Operator module 3042 and the second computational submodule 3043.
The determination submodule 3041, for determining the first weight and the second weight of expression score and answer score respectively;
First computational submodule 3042, for using Weight algorithm, computational chart mutual affection number multiplies with the first of the first weight
Product calculates the second product of answer score and the second weight;
Second computational submodule 3043, for calculating the sum of products of the first product Yu the second product, using sum of products as
Evaluation result.
In specific application scenarios, as shown in FIGURE 3 E, which further includes statistical module 307, enquiry module 308 and is returned
Return module 309.
The statistical module 307 will go out for counting the frequency of occurrences of each expression data in preset number expression data
Existing frequency is ranked up from big to small;
The enquiry module 308 is inquired for obtaining the corresponding target expression data of the frequency of occurrences to rank the first and determines mesh
The corresponding target personality of expression data is marked, using target personality as the personality prediction result of user;
The return module 309, for returning to evaluation result and personality default result.
Device provided in an embodiment of the present invention extracts in image data when instruction is submitted in the answer for receiving user
User inputs the preset number expression data when answer of the problem of preset number, and obtains preset number expression data respectively
The first score of corresponding preset number, calculates the summation of the first score of preset number, obtains expression score, obtains respectively pre-
If the problem of number answer the second score of corresponding preset number, calculates the summation of the second score of preset number, is answered
Case score calculates expression score and answer score using Weight algorithm, generates evaluation result, so that the evaluation and test generated
As a result the problem of not only allowing for user's input answer, it is also contemplated that user is in expression when evaluating and testing topic of answering, evaluation result
The true idea being more close to the users, measures are more diversified, and obtained evaluation result accuracy is higher.
It should be noted that each functional unit involved by a kind of evaluation result generating means provided in an embodiment of the present invention
Other are accordingly described, can be with reference to the corresponding description in Fig. 1 and Fig. 2, and details are not described herein.
In the exemplary embodiment, referring to fig. 4, a kind of equipment is additionally provided, which includes communication bus, processing
Device, memory and communication interface, can also include, input/output interface and display equipment, wherein can between each functional unit
To complete mutual communication by bus.The memory is stored with computer program, processor, for executing institute on memory
The program of storage executes the evaluation result generation method in above-described embodiment.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of evaluation result generation method is realized when row.
Through the above description of the embodiments, those skilled in the art can be understood that the application can lead to
Hardware realization is crossed, the mode of necessary general hardware platform can also be added to realize by software.Based on this understanding, this Shen
Technical solution please can be embodied in the form of software products, which can store in a non-volatile memories
In medium (can be CD-ROM, USB flash disk, mobile hard disk etc.), including some instructions are used so that a computer equipment (can be
Personal computer, server or network equipment etc.) execute method described in each implement scene of the application.
It will be appreciated by those skilled in the art that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, module in attached drawing or
Process is not necessarily implemented necessary to the application.
It will be appreciated by those skilled in the art that the module in device in implement scene can be described according to implement scene into
Row is distributed in the device of implement scene, can also be carried out corresponding change and is located at the one or more dresses for being different from this implement scene
In setting.The module of above-mentioned implement scene can be merged into a module, can also be further split into multiple submodule.
Above-mentioned the application serial number is for illustration only, does not represent the superiority and inferiority of implement scene.
Disclosed above is only several specific implementation scenes of the application, and still, the application is not limited to this, Ren Heben
What the technical staff in field can think variation should all fall into the protection scope of the application.
Claims (10)
1. a kind of evaluation result generation method characterized by comprising
When instruction is submitted in the answer for receiving user, the problem of user inputs preset number is extracted in image data and is answered
Preset number expression data when case, described image data are that the user distinguishes when answer the problem of inputting preset number
The image data of acquisition;
The preset number expression data the first score of corresponding preset number is obtained respectively, calculates the preset number
The summation of first score obtains expression score;
The problem of obtaining the preset number respectively answer the second score of corresponding preset number, calculates the preset number
The summation of second score obtains answer score;
Using Weight algorithm, the expression score and the answer score are calculated, generate evaluation result.
2. the method according to claim 1, wherein it is described when receive user answer submit instruction when,
Before preset number expression data when extracting the problem of user inputs preset number answer in image data, the side
Method further include:
In the risk evaluation and test request for receiving user, the evaluation and test topic of preset number is transmitted to user;
Starting acquisition equipment, acquires described image data based on the acquisition equipment.
3. the method according to claim 1, wherein it is described when receive user answer submit instruction when,
Preset number expression data when the problem of user inputs preset number answer is extracted in image data, comprising:
When receiving the answer and submitting instruction, the problem of determining the preset number respectively answer is in described image data
The fragment data of corresponding preset number;
It determines the image scaled of described image data, obtains multiple sample expressions with described image ratio match;
For each fragment data in the fragment data of the preset number, the fragment data and the multiple sample are calculated
Multiple similarities between expression;
The multiple similarity is ranked up from big to small, extracts the sample expression of the similarity instruction to rank the first as institute
State the expression data of fragment data;
The process of the similarity between above-mentioned calculating fragment data and the multiple sample expression is repeated, is obtained described default
The corresponding preset number expression data of the fragment data of number.
4. according to the method described in claim 3, it is characterized in that, described when receiving the answer submission instruction, difference
The fragment data of the problem of determining preset number answer corresponding preset number in described image data, comprising:
When receiving the answer submission instruction, the consuming of user answer the problem of inputting the preset number is obtained
Time maps the consuming time and described image data on a timeline;
According to the time of answer the problem of receiving the preset number, on the time axis to consuming time and described
Image data is divided, and the fragment data of the preset number is obtained.
5. according to the method described in claim 3, it is characterized in that, every in the fragment data for the preset number
A fragment data calculates multiple similarities between the fragment data and the multiple sample expression, comprising:
It is the fragment data and the multiple sample table for each fragment data in the fragment data of the preset number
Feelings establish coordinate system;
For each sample expression in the multiple sample expression, respectively in the fragment data and the sample expression
Extract the first object point of target numbers and the second target point of target numbers;
Count for the target point being overlapped in the first object point of the target numbers and the second target point of the target numbers
Number, using the number as the similarity between the fragment data and the sample expression;
The process for repeating the similarity between above-mentioned determining fragment data and sample expression, determines the fragment data and institute
State multiple similarities between multiple sample expressions.
6. the method according to claim 1, wherein described use Weight algorithm, to the expression score and institute
It states answer score to be calculated, generates evaluation result, comprising:
The first weight and the second weight of the expression score and the answer score are determined respectively;
Using the Weight algorithm, the first product of the expression score Yu first weight is calculated, calculates the answer point
Several the second products with second weight;
The sum of products for calculating first product Yu second product, using the sum of products as the evaluation result.
7. the method according to claim 1, wherein the method also includes:
The frequency of occurrences of each expression data in the preset number expression data is counted, from big to small by the frequency of occurrences
It is ranked up;
The corresponding target expression data of the frequency of occurrences to rank the first is obtained, inquiry determines the corresponding mesh of the target expression data
Personality is marked, using the target personality as the personality prediction result of the user;
The evaluation result and the personality default result are returned.
8. a kind of evaluation result generating means characterized by comprising
Extraction module, for it is pre- to extract user's input in image data when instruction is submitted in the answer for receiving user
If the preset number expression data when answer of the problem of number, described image data are the user in input preset number
The image data acquired respectively when problem answers;
First computing module, for obtaining the preset number expression data the first score of corresponding preset number respectively,
The summation for calculating the first score of the preset number, obtains expression score;
Second computing module, the second score of the corresponding preset number of answer the problem of for obtaining the preset number respectively,
The summation for calculating the second score of the preset number, obtains answer score;
Generation module calculates the expression score and the answer score, generates evaluation and test knot for using Weight algorithm
Fruit.
9. a kind of equipment, including memory and processor, the memory are stored with computer program, which is characterized in that described
The step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811534540.2A CN109872026A (en) | 2018-12-14 | 2018-12-14 | Evaluation result generation method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811534540.2A CN109872026A (en) | 2018-12-14 | 2018-12-14 | Evaluation result generation method, device, equipment and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109872026A true CN109872026A (en) | 2019-06-11 |
Family
ID=66917080
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811534540.2A Pending CN109872026A (en) | 2018-12-14 | 2018-12-14 | Evaluation result generation method, device, equipment and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109872026A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111210685A (en) * | 2020-01-08 | 2020-05-29 | 郑州市金水区大山培训学校有限公司 | Method, device and equipment for testing knowledge mastering conditions |
CN111222774A (en) * | 2019-12-30 | 2020-06-02 | 广州博士信息技术研究院有限公司 | Enterprise data analysis method and device and server |
CN111339859A (en) * | 2020-02-17 | 2020-06-26 | 出门问问信息科技有限公司 | Multi-modal risk control method and device and computer-readable storage medium |
CN112102125A (en) * | 2020-08-31 | 2020-12-18 | 湖北美和易思教育科技有限公司 | Student skill evaluation method and device based on facial recognition |
CN112819609A (en) * | 2021-02-24 | 2021-05-18 | 深圳前海微众银行股份有限公司 | Risk assessment method, apparatus, computer-readable storage medium, and program product |
CN114399827A (en) * | 2022-03-14 | 2022-04-26 | 潍坊护理职业学院 | College graduate career personality testing method and system based on facial micro-expression |
CN114973374A (en) * | 2022-05-31 | 2022-08-30 | 平安银行股份有限公司 | Expression-based risk evaluation method, device, equipment and storage medium |
CN117853977A (en) * | 2024-01-04 | 2024-04-09 | 北京小懂科技有限公司 | Method, system, equipment and medium for intelligent evaluation through video |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005293027A (en) * | 2004-03-31 | 2005-10-20 | Sumitomo Mitsui Banking Corp | Method and system for evaluation of evaluation object |
CN101482919A (en) * | 2008-01-08 | 2009-07-15 | 欧姆龙株式会社 | Face collation apparatus |
JP2009251938A (en) * | 2008-04-07 | 2009-10-29 | Value Resource Design Inc | Evaluation system, evaluation method and evaluation program |
CN105405436A (en) * | 2014-09-05 | 2016-03-16 | 欧姆龙株式会社 | Scoring device and scoring method |
CN106815309A (en) * | 2016-12-20 | 2017-06-09 | 北京奇虎科技有限公司 | A kind of image method for pushing, device and mobile terminal |
CN107704834A (en) * | 2017-10-13 | 2018-02-16 | 上海壹账通金融科技有限公司 | Householder method, device and storage medium are examined in micro- expression face |
CN108335198A (en) * | 2018-02-07 | 2018-07-27 | 平安科技(深圳)有限公司 | Customer risk assessment method, device, equipment and computer readable storage medium |
CN108629694A (en) * | 2018-05-16 | 2018-10-09 | 北京京东尚科信息技术有限公司 | Risk control system and method and computer readable storage medium |
CN108888277A (en) * | 2018-04-26 | 2018-11-27 | 深圳市科思创动科技有限公司 | Psychological test method, system and terminal device |
-
2018
- 2018-12-14 CN CN201811534540.2A patent/CN109872026A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005293027A (en) * | 2004-03-31 | 2005-10-20 | Sumitomo Mitsui Banking Corp | Method and system for evaluation of evaluation object |
CN101482919A (en) * | 2008-01-08 | 2009-07-15 | 欧姆龙株式会社 | Face collation apparatus |
JP2009251938A (en) * | 2008-04-07 | 2009-10-29 | Value Resource Design Inc | Evaluation system, evaluation method and evaluation program |
CN105405436A (en) * | 2014-09-05 | 2016-03-16 | 欧姆龙株式会社 | Scoring device and scoring method |
CN106815309A (en) * | 2016-12-20 | 2017-06-09 | 北京奇虎科技有限公司 | A kind of image method for pushing, device and mobile terminal |
CN107704834A (en) * | 2017-10-13 | 2018-02-16 | 上海壹账通金融科技有限公司 | Householder method, device and storage medium are examined in micro- expression face |
CN108335198A (en) * | 2018-02-07 | 2018-07-27 | 平安科技(深圳)有限公司 | Customer risk assessment method, device, equipment and computer readable storage medium |
CN108888277A (en) * | 2018-04-26 | 2018-11-27 | 深圳市科思创动科技有限公司 | Psychological test method, system and terminal device |
CN108629694A (en) * | 2018-05-16 | 2018-10-09 | 北京京东尚科信息技术有限公司 | Risk control system and method and computer readable storage medium |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111222774A (en) * | 2019-12-30 | 2020-06-02 | 广州博士信息技术研究院有限公司 | Enterprise data analysis method and device and server |
CN111210685A (en) * | 2020-01-08 | 2020-05-29 | 郑州市金水区大山培训学校有限公司 | Method, device and equipment for testing knowledge mastering conditions |
CN111339859A (en) * | 2020-02-17 | 2020-06-26 | 出门问问信息科技有限公司 | Multi-modal risk control method and device and computer-readable storage medium |
CN112102125A (en) * | 2020-08-31 | 2020-12-18 | 湖北美和易思教育科技有限公司 | Student skill evaluation method and device based on facial recognition |
CN112819609A (en) * | 2021-02-24 | 2021-05-18 | 深圳前海微众银行股份有限公司 | Risk assessment method, apparatus, computer-readable storage medium, and program product |
CN114399827A (en) * | 2022-03-14 | 2022-04-26 | 潍坊护理职业学院 | College graduate career personality testing method and system based on facial micro-expression |
CN114973374A (en) * | 2022-05-31 | 2022-08-30 | 平安银行股份有限公司 | Expression-based risk evaluation method, device, equipment and storage medium |
CN117853977A (en) * | 2024-01-04 | 2024-04-09 | 北京小懂科技有限公司 | Method, system, equipment and medium for intelligent evaluation through video |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109872026A (en) | Evaluation result generation method, device, equipment and computer readable storage medium | |
CN108833458B (en) | Application recommendation method, device, medium and equipment | |
CN108921569B (en) | Method and device for determining complaint type of user | |
US20210311751A1 (en) | Machine-learning models applied to interaction data for determining interaction goals and facilitating experience-based modifications to interface elements in online environments | |
CN109684947A (en) | Mark quality control method, device, computer equipment and storage medium | |
CN110413888B (en) | Book recommendation method and device | |
EP4167194A1 (en) | Key point detection method and apparatus, model training method and apparatus, device and storage medium | |
CN111782947A (en) | Search content display method and device, electronic equipment and storage medium | |
CN109325818B (en) | Product recommendation method, computer readable storage medium and terminal equipment | |
CN113902956A (en) | Training method of fusion model, image fusion method, device, equipment and medium | |
CN106600360B (en) | Method and device for sorting recommended objects | |
CN113705792B (en) | Personalized recommendation method, device, equipment and medium based on deep learning model | |
CN114579523A (en) | Double-recording file quality inspection method and device, computer equipment and storage medium | |
CN116340831B (en) | Information classification method and device, electronic equipment and storage medium | |
CN113704452B (en) | Data recommendation method, device, equipment and medium based on Bert model | |
CN115408606A (en) | Insurance information pushing method and device, storage medium and computer equipment | |
CN113343700A (en) | Data processing method, device, equipment and storage medium | |
CN113849618A (en) | Strategy determination method and device based on knowledge graph, electronic equipment and medium | |
Vejdemo-Johansson et al. | Certified mapper: Repeated testing for acyclicity and obstructions to the nerve lemma | |
CN114048148A (en) | Crowdsourcing test report recommendation method and device and electronic equipment | |
CN111639874A (en) | Rating method and related equipment | |
CN111915339A (en) | Data processing method, device and equipment | |
US20220261666A1 (en) | Leveraging big data, statistical computation and artificial intelligence to determine a likelihood of object renunciation prior to a resource event | |
CN110955755A (en) | Method and system for determining target standard information | |
JP7345744B2 (en) | data processing equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |