Personnel portrait information intelligent generation method and system based on multiple angles

Abstract

The invention relates to the technical field of computers, in particular to a method and a system for intelligently generating personnel portrait information based on multiple angles. The method comprises the following steps: acquiring data information in a training set, preprocessing the data information, determining a domain label of a corresponding person, checking each domain label, determining a domain weight, constructing person portrait information of the person, comparing the person portrait information with preset person portrait information in the training set, and judging based on a comparison result. A corresponding processing instruction is generated based on the judgment result, operation parameters in the construction process are re-determined based on the processing instruction, and the system comprises a data acquisition unit, a preprocessing unit, a domain extraction unit, a label checking unit, a weight generation unit, a portrait construction unit, an analysis unit and a control unit. According to the invention, real-time monitoring and intelligent adjustment of the intelligent generation process of the multi-angle personnel portrait information are effectively realized, and the intelligent generation efficiency of the multi-angle personnel portrait information is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and system for intelligently generating personnel portrait information based on multiple angles. Background Art

[0002] Determining the portrait information of scientific researchers from a single perspective has important purposes in scientific research management, resource allocation, academic exchanges and talent training. However, a single perspective cannot fully present the full picture of scientific researchers. Determining the portrait information of researchers from multiple perspectives is to comprehensively characterize and describe the characteristics of scientific researchers from multiple dimensions. Determining the portrait information of scientific researchers from multiple perspectives is of great significance in comprehensively evaluating scientific research capabilities, optimizing scientific research resource allocation, promoting scientific research cooperation and exchanges, assisting in the training of scientific research talents and supporting scientific research decision-making.

[0003] Chinese Patent Publication No.: CN117332297A discloses a method, device, medium and equipment for determining the portrait information of scientific researchers. First, the input information and classification rules are obtained. Secondly, the labels in the classification information are determined according to the classification rules. The matched ones are used as static labels, and the unmatched ones are used as dynamic labels. Finally, based on the output results, the target label is selected, and the portrait information is determined according to the target label. By determining the dynamic and static labels of the scientific researchers, and then selecting the target label and marking the corresponding scientific researchers, the multi-angle information of the scientific researchers is fully utilized.

[0004] It can be seen that the above scheme enables the institutions to which researchers belong to understand the single-angle portrait information of the corresponding researchers through static tags, and also allows them to use dynamic tags to fully understand the corresponding researchers. However, the above scheme cannot achieve real-time monitoring and intelligent adjustment of the intelligent generation process of multi-angle personnel portrait information, and thus cannot guarantee the efficiency of the intelligent generation of multi-angle personnel portrait information. Summary of the invention

[0005] To this end, the present invention provides a method and system for intelligently generating personnel portrait information based on multiple angles, so as to overcome the problem in the prior art that the intelligent generation process of multi-angle personnel portrait information cannot be monitored and adjusted intelligently, resulting in low efficiency of intelligent generation of multi-angle personnel portrait information.

[0006] On the one hand, the present invention provides a method for intelligently generating personnel portrait information based on multiple angles, comprising: Obtain data information of several people in the training set, including personal data and scientific research results data; Preprocessing the data information to filter out redundant data; Determine the field label of the corresponding person according to the preprocessed scientific research achievement data; For a single person, the data information is checked to determine the classification of the field label; Determining the domain weight of each of the domain labels; Constructing personnel profile information of personnel based on the weights of each of the aforementioned fields; Comparing the personnel portrait information with the preset personnel portrait information in the training set; Making a determination on the construction of the personnel portrait information based on the comparison result; Generate corresponding processing instructions based on the judgment results, Or, completing the construction of the personnel portrait information; Wherein, the determination includes determining whether the construction of the personnel portrait information is qualified and determining the reasons for failure; The operating parameters in the personnel portrait information construction process are re-determined based on the received processing instructions.

[0007] Furthermore, the process of determining the construction of the personnel portrait information based on the comparison result includes: Determine the number of domain tags that match the domain tags in the personnel portrait information with the preset domain tags in the preset personnel portrait information, and record the obtained number as the total number of domain tag matches; Counting the number of the preset domain tags, and recording the obtained number as the total number of preset domain tags; Calculating the ratio of the total number of domain label matches to the total number of preset domain labels, and recording the obtained ratio as the domain label matching degree; When the domain label matching degree is greater than the second preset domain label matching degree, determining that the determination of the domain label is qualified, and determining whether the determination of the domain weight of each domain label is qualified; When the domain label matching degree is less than or equal to the second preset domain label matching degree and greater than the first preset domain label matching degree, determining that the determination of the domain label is unqualified, and determining whether the determination of the domain label is qualified based on the number of domain labels; When the domain label matching degree is less than or equal to the first preset domain label matching degree, it is determined that the determination of the domain label is unqualified, and the reason for the unqualified determination of the domain label is determined based on the domain label matching degree.

[0008] Furthermore, the process of determining whether the domain weight of each domain label is qualified includes: Calculating the ratio of each of the field weights to the corresponding each of the preset field weights, and recording the obtained ratio as the field weight ratio; For each of the domain weights, the absolute value of the difference between the domain weight ratio and the domain weight standard is calculated, and the obtained absolute value is recorded as the domain weight error; Completing the calculation of the domain weight error of each of the domain weights in sequence; When the domain weight error is less than the preset domain weight error, determining that the domain weight corresponding to the domain weight error matches the preset domain weight; Based on the matching situation, it is determined whether the determination of the field weight of each field label is qualified.

[0009] Furthermore, the process of determining whether the domain weight of each domain tag is qualified based on the matching situation includes: Recording the matched domain weight and the preset domain weight as a matching domain label group; Counting the number of matching domain label groups, and recording the obtained number as the number of matching label groups; Determine the number of the domain weights compared with the domain weight errors and the preset domain weights, and record the obtained number as the number of label groups; Calculating the ratio of the number of matching tag groups to the number of tag groups, and recording the obtained ratio as the tag group matching ratio; Determining whether the determination of the field weight of each field tag is qualified based on the tag group matching ratio; When the tag group matching ratio is greater than the preset tag group matching ratio, it is determined that the determination of the field weight of each field tag is qualified, and the construction of the personnel portrait information is completed; When the tag group matching ratio is less than or equal to the preset tag group matching ratio, it is determined that the determination of the field weight of each field label is unqualified, the preprocessing of the data information does not meet the standard, and the duplicate checking standard in the preprocessing process is corrected based on the tag group matching ratio.

[0010] Furthermore, the process of correcting the duplicate checking standard in the preprocessing process based on the tag group matching ratio includes: Calculating the difference between the preset tag group matching ratio and the tag group matching ratio, and recording the obtained difference as the tag group matching difference; The duplicate checking standard is increased based on the tag group matching difference, and the increase in the duplicate checking standard is proportional to the tag group matching difference.

[0011] Further, the process of determining whether the determination of the domain tags is qualified based on the number of the domain tags includes: Determine the number of the domain labels, and record the obtained number as the number of domain labels; Determining whether the determination of the field label is qualified based on the number of field labels; When the number of the field tags is less than or equal to the preset number of field tags, determining that the field tags are qualified, and determining the field weights of the classified field tags; When the number of domain tags is greater than the preset number of domain tags, it is determined that the determination of the domain tags is unqualified, and the reason why the determination of the domain tags is unqualified is determined based on the domain tag matching degree.

[0012] Furthermore, the process of determining the reason why the determination of the domain label is unqualified based on the domain label matching degree includes: Calculating the difference between the second preset domain label matching degree and the domain label matching degree, and recording the obtained difference as the label matching degree difference; Determining the reason why the determination of the field label is unqualified based on the label matching difference; When the label matching difference is less than the preset label matching difference, it is determined that the reason for the determination of the field label is unqualified is that the field division in the process of determining the field label of the corresponding person according to the preprocessed scientific research achievement data does not meet the standard, and the field division is corrected based on the label matching difference; When the tag matching difference is greater than or equal to the preset tag matching difference, it is determined that the reason for the determination of the field tag failure is that the data information does not meet the standard, and whether the data information is repeated is checked.

[0013] Furthermore, the process of correcting the domain division based on the tag matching difference includes: Determining the preset frequency in the process of said field division; Calculating the ratio of the tag matching difference to a preset tag matching difference, and recording the obtained ratio as the tag matching ratio; The preset frequency is reduced based on the tag matching ratio, and the reduction range of the preset frequency is proportional to the tag matching ratio.

[0014] Furthermore, the process of checking whether the data information is repeated includes: When the verification result shows that the data information is duplicated, the data information is screened out again, and the personnel portrait information is reconstructed; When the verification result shows that there is no duplicate data information, it is determined that the quantity of the scientific research achievement data does not meet the standards, and a notice is issued to increase the quantity of scientific research achievement data to be obtained.

[0015] On the other hand, the present invention also provides a system for intelligently generating personnel portrait information based on multiple angles, comprising: A data acquisition unit, used to acquire data information of several people in the training set, including personal data and scientific research results data; A preprocessing unit, connected to the data acquisition unit, for preprocessing the data information to filter out redundant data; A domain extraction unit, which is connected to the preprocessing unit and is used to determine the domain label of the corresponding person according to the preprocessed scientific research achievement data; A label checking unit, which is connected to the field extraction unit and is used for checking the data information for a single person to determine the classification of the field label; A weight generating unit, connected to the label checking unit, for determining the domain weight of each of the domain labels; A portrait construction unit, which is connected to the weight generation unit and is used to construct personnel portrait information of personnel based on the weights of each field; An analysis unit connected to the portrait construction unit, used to compare the personnel portrait information with the preset personnel portrait information in the training set; the analysis unit is also used to make a determination on the construction of the personnel portrait information based on the comparison result; the analysis unit is also used to generate a corresponding processing instruction based on the determination result, or complete the construction of the personnel portrait information; wherein the determination includes determining whether the construction of the personnel portrait information is qualified and determining the reason for failure; A control unit, which is respectively connected to the preprocessing unit, the field extraction unit, the label checking unit and the analysis unit, and is used to redetermine the operating parameters in the process of constructing the personnel portrait information based on the received processing instructions. Compared with the prior art, the beneficial effect of the present invention lies in that the present invention compares the personnel portrait information with the preset personnel portrait information in the training set, and makes a judgment on the construction of the personnel portrait information based on the comparison result, wherein the judgment includes whether the construction of the personnel portrait information is qualified and the reason for the unqualified judgment. The present invention effectively realizes real-time monitoring of the intelligent generation process of multi-angle personnel portrait information, generates corresponding processing instructions based on the judgment results, or completes the construction of the personnel portrait information, and re-determines the operating parameters in the process of constructing the personnel portrait information based on the received processing instructions. While effectively realizing the intelligent adjustment of the intelligent generation process of multi-angle personnel portrait information, the intelligent generation efficiency of multi-angle personnel portrait information is effectively improved.

[0016] Furthermore, the present invention makes judgments on the construction of personnel portrait information based on the degree of domain label matching, and can timely and accurately complete the judgment on the construction of personnel portrait information. While further realizing real-time monitoring of the intelligent generation process of multi-angle personnel portrait information, it further improves the efficiency of the intelligent generation of multi-angle personnel portrait information.

[0017] Furthermore, when the present invention determines whether the determination of the field label is qualified, it determines whether the determination of the field weight of each field label is qualified, and completes the calculation of the field weight error of each field weight in turn to determine the matching situation. It can accurately complete the field weight error analysis of the field weight, and further improve the efficiency of the intelligent generation of multi-angle personnel portrait information.

[0018] Furthermore, the present invention determines whether the field weight of each field label is qualified based on the label group matching ratio, can accurately determine whether the field weight is qualified, and further realizes real-time monitoring of the intelligent generation process of multi-angle personnel portrait information. When the preprocessing of data information does not meet the standards, the duplicate checking standards in the preprocessing process are corrected based on the label group matching ratio, further improving the intelligent generation efficiency of multi-angle personnel portrait information.

[0019] Furthermore, when the preprocessing of data information does not meet the standards, the present invention increases the duplicate checking standards based on the tag group matching difference, so as to avoid the situation where the preprocessing of data information does not meet the standards due to the duplicate checking standards not meeting the standards. While further realizing the intelligent adjustment of the intelligent generation process of multi-angle personnel portrait information, the intelligent generation efficiency of multi-angle personnel portrait information is further improved.

[0020] Furthermore, the present invention determines that the determination of the domain label is unqualified when the domain label matching degree is less than or equal to the second preset domain label matching degree and greater than the first preset domain label matching degree, and determines whether the determination of the domain label is qualified based on the number of domain labels, thereby avoiding the occurrence of misjudgment. While further realizing real-time monitoring of the intelligent generation process of multi-angle personnel portrait information, the intelligent generation efficiency of multi-angle personnel portrait information is further improved.

[0021] Furthermore, the present invention determines the reason for the unqualified domain label based on the label matching degree difference, and can timely and accurately complete the determination of the reason for the unqualified domain label. While further realizing real-time monitoring of the intelligent generation process of multi-angle personnel portrait information, it further improves the efficiency of the intelligent generation of multi-angle personnel portrait information.

[0022] Furthermore, the present invention reduces the preset frequency based on the label matching ratio when the label matching difference is less than the preset label matching difference, thereby avoiding the occurrence of a situation where the field division does not meet the standard due to the preset frequency not meeting the standard. This further realizes intelligent adjustment of the intelligent generation process of multi-angle personnel portrait information, and further improves the intelligent generation efficiency of multi-angle personnel portrait information.

[0023] Furthermore, when the label matching difference is greater than or equal to a preset label matching difference, the present invention verifies whether there is duplication in the data information, effectively avoiding the misjudgment between the need to re-screen the data information and the fact that the number of scientific research achievement data does not meet the standards, and re-screens the data information or issues a notification that the number of scientific research achievement data needs to be increased, effectively avoiding the occurrence of a situation where the label matching degree does not meet the standards, while further realizing intelligent adjustment of the intelligent generation process of multi-angle personnel portrait information, and further improving the intelligent generation efficiency of multi-angle personnel portrait information.

[0024] Furthermore, the present invention, by setting up a data acquisition unit, a preprocessing unit, a field extraction unit, a label verification unit, a weight generation unit, a portrait construction unit, an analysis unit and a control unit, and the units are connected as a system, effectively ensuring the efficiency of using the method of intelligent generation of personnel portrait information based on multiple angles, while further realizing real-time monitoring and intelligent adjustment of the intelligent generation process of personnel portrait information from multiple angles, further improving the efficiency of intelligent generation of personnel portrait information from multiple angles. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a structural block diagram of a system for intelligently generating personnel portrait information based on multiple angles according to an embodiment of the present invention; Figure 2 It is a flow chart of a method for intelligently generating personnel portrait information based on multiple angles according to an embodiment of the present invention; Figure 3 A flowchart for determining whether the construction of personnel portrait information is qualified according to an embodiment of the present invention; Figure 4 A flow chart of determining the reasons why the construction of personnel portrait information is unqualified according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0027] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0028] See also Figure 1 As shown, it is a structural block diagram of the intelligent generation system of personnel portrait information based on multiple angles according to an embodiment of the present invention. The system according to the embodiment of the present invention includes a data acquisition unit, a preprocessing unit, a domain extraction unit, a label checking unit, a weight generation unit, a portrait construction unit, an analysis unit and a control unit; wherein, The data acquisition unit is used to acquire data information of several persons in the training set, the data information including personal data and scientific research results data; The preprocessing unit is connected to the data acquisition unit and is used to preprocess the data information to filter out redundant data; The field extraction unit is connected to the preprocessing unit, and is used to determine the field label of the corresponding person according to the preprocessed scientific research achievement data; The label checking unit is connected to the field extraction unit and is used to check the data information for a single person to determine the classification of the field label; The weight generating unit is connected to the label checking unit and is used to determine the domain weight of each domain label; The portrait construction unit is connected to the weight generation unit, and is used to construct personnel portrait information of personnel based on the weights of each field; The analysis unit is connected to the portrait construction unit and is used to compare the personnel portrait information with the preset personnel portrait information in the training set; The analysis unit is also used to determine the construction of the personnel portrait information based on the comparison result; The analysis unit is also used to generate corresponding processing instructions based on the determination result. Or, completing the construction of the personnel portrait information; Wherein, the determination includes determining whether the construction of the personnel portrait information is qualified and determining the reasons for failure; The control unit is respectively connected to the preprocessing unit, the field extraction unit, the label checking unit and the analysis unit, so as to redetermine the operating parameters in the process of constructing the personnel portrait information based on the received processing instructions.

[0029] See also Figure 2 As shown, it is a flow chart of a method for intelligently generating personnel portrait information based on multiple angles according to an embodiment of the present invention. The method according to the embodiment of the present invention includes: Obtain data information of several people in the training set, including personal data and scientific research results data; Preprocessing the data information to filter out redundant data; Determine the field label of the corresponding person according to the preprocessed scientific research achievement data; For a single person, the data information is checked to determine the classification of the field label; Determining the domain weight of each of the domain labels; Constructing personnel profile information of personnel based on the weights of each of the aforementioned fields; Comparing the personnel portrait information with the preset personnel portrait information in the training set; Making a determination on the construction of the personnel portrait information based on the comparison result; Generate corresponding processing instructions based on the judgment results, Or, completing the construction of the personnel portrait information; Wherein, the determination includes determining whether the construction of the personnel portrait information is qualified and determining the reasons for failure; The operating parameters in the personnel portrait information construction process are re-determined based on the received processing instructions.

[0030] See also Figure 3 As shown, it is a flow chart of determining whether the construction of personnel portrait information is qualified according to an embodiment of the present invention. The process of determining the construction of the personnel portrait information based on the comparison result according to the embodiment of the present invention includes: Determine the number of domain tags that match the domain tags in the personnel portrait information with the preset domain tags in the preset personnel portrait information, and record the obtained number as the total number of domain tag matches; Counting the number of the preset domain tags, and recording the obtained number as the total number of preset domain tags; Calculating the ratio of the total number of domain label matches to the total number of preset domain labels, and recording the obtained ratio as the domain label matching degree; Determining the construction of the personnel portrait information based on the matching degree of the field labels; When the domain label matching degree is greater than the second preset domain label matching degree M2, it is determined that the determination of the domain label is qualified, and whether the determination of the domain weight of each domain label is qualified is determined. In this embodiment, the second preset domain label matching degree M2=87.5%; When the domain label matching degree is less than or equal to the second preset domain label matching degree M2 and greater than the first preset domain label matching degree M1, it is determined that the determination of the domain label is unqualified, and whether the determination of the domain label is qualified is determined based on the number of domain labels, wherein the first preset domain label matching degree M1 in this embodiment is 73.9%; When the domain label matching degree is less than or equal to the first preset domain label matching degree M1, it is determined that the determination of the domain label is unqualified, and the reason for the unqualified determination of the domain label is determined based on the domain label matching degree.

[0031] Please continue reading Figure 3 As shown, the process of determining whether the domain weight of each domain label is qualified in the embodiment of the present invention includes: Calculating the ratio of each of the field weights to the corresponding each of the preset field weights, and recording the obtained ratio as the field weight ratio; For each of the domain weights, the absolute value of the difference between the domain weight ratio and the domain weight standard S is calculated, and the obtained absolute value is recorded as the domain weight error, wherein the domain weight standard S=1 in this embodiment; Completing the calculation of the domain weight error of each of the domain weights in sequence; When the domain weight error is less than the preset domain weight error E, it is determined that the domain weight corresponding to the domain weight error matches the preset domain weight, wherein the preset domain weight error E in this embodiment is 0.06; Based on the matching situation, it is determined whether the determination of the field weight of each field label is qualified.

[0032] Please continue reading Figure 3 As shown, the process of determining whether the domain weight of each domain tag is qualified based on the matching situation in the embodiment of the present invention includes: Recording the matched domain weight and the preset domain weight as a matching domain label group; Counting the number of matching domain label groups, and recording the obtained number as the number of matching label groups; Determine the number of the domain weights compared with the domain weight errors and the preset domain weights, and record the obtained number as the number of label groups; Calculating the ratio of the number of matching tag groups to the number of tag groups, and recording the obtained ratio as the tag group matching ratio; Determining whether the determination of the field weight of each field tag is qualified based on the tag group matching ratio; When the tag group matching ratio is greater than the preset tag group matching ratio R, it is determined that the determination of the field weight of each field tag is qualified, and the construction of the personnel portrait information is completed. In this embodiment, the preset tag group matching ratio R=88.9%; When the tag group matching ratio is less than or equal to the preset tag group matching ratio R, it is determined that the determination of the field weight of each field label is unqualified, the preprocessing of the data information does not meet the standard, and the duplicate checking standard in the preprocessing process is corrected based on the tag group matching ratio.

[0033] Please continue reading Figure 3 As shown, the process of correcting the duplicate checking standard in the preprocessing process based on the tag group matching ratio in the embodiment of the present invention includes: Calculating the difference between the preset tag group matching ratio and the tag group matching ratio, and recording the obtained difference as the tag group matching difference; Increase the duplicate checking standard based on the tag group matching difference; When the tag group matching difference is greater than the second preset tag group matching difference △D2, the duplication checking standard is increased to 1.19 times the initial duplication checking standard, wherein the second preset tag group matching difference △D2 in this embodiment is 63.2%; When the tag group matching difference is less than or equal to the second preset tag group matching difference △D2 and greater than the first preset tag group matching difference △D1, the duplication checking standard is increased to 1.13 times the initial duplication checking standard, wherein the first preset tag group matching difference △D1 in this embodiment is 39.6%; When the tag group matching difference is less than or equal to the first preset tag group matching difference ΔD1, the duplication checking standard is increased to 1.06 times of the initial duplication checking standard.

[0034] Please continue reading Figure 3 As shown, the process of determining whether the determination of the domain label is qualified based on the number of the domain labels in the embodiment of the present invention includes: Determine the number of the domain labels, and record the obtained number as the number of domain labels; Determining whether the determination of the field label is qualified based on the number of field labels; When the number of domain tags is less than or equal to the preset number of domain tags N, the determination of the domain tags is determined to be qualified, and the domain weights of the classified domain tags are determined, wherein the preset number of domain tags N=3 in this embodiment; When the number of domain tags is greater than the preset number N of domain tags, it is determined that the determination of the domain tags is unqualified, and the reason why the determination of the domain tags is unqualified is determined based on the domain tag matching degree.

[0035] See also Figure 4 As shown, it is a flow chart of determining the reason why the construction of personnel portrait information is unqualified according to an embodiment of the present invention. The process of determining the reason why the determination of the field label is unqualified based on the field label matching degree according to an embodiment of the present invention includes: Calculating the difference between the second preset domain label matching degree and the domain label matching degree, and recording the obtained difference as the label matching degree difference; Determining the reason why the determination of the field label is unqualified based on the label matching difference; When the label matching difference is less than the preset label matching difference △B, it is determined that the reason for the determination of the field label is unqualified is that the field division in the process of determining the field label of the corresponding person according to the preprocessed scientific research achievement data does not meet the standard, and the field division is corrected based on the label matching difference, wherein the preset label matching difference △B in this embodiment is 58.7%; When the tag matching degree difference is greater than or equal to the preset tag matching degree difference ΔB, it is determined that the reason for the determination of the field tag failure is that the data information does not meet the standard, and the data information is checked for duplication.

[0036] Please continue reading Figure 4 As shown, the process of correcting the field division based on the tag matching difference in the embodiment of the present invention includes: Determining the preset frequency in the process of said field division; Calculating the ratio of the tag matching difference to a preset tag matching difference, and recording the obtained ratio as the tag matching ratio; Reducing the preset frequency based on the tag matching ratio; When the tag matching ratio is greater than the second preset tag matching ratio L2, the preset frequency is reduced to 0.81 times the initial preset frequency, wherein the second preset tag matching ratio L2 in this embodiment is 68.5%; When the tag matching ratio is less than or equal to the second preset tag matching ratio L2 and greater than the first preset tag matching ratio L1, the preset frequency is reduced to 0.87 times the initial preset frequency, wherein the first preset tag matching ratio L1 in this embodiment is 38.3%; When the tag matching ratio is less than or equal to the first preset tag matching ratio L1, reducing the preset frequency to 0.93 times the initial preset frequency; Specifically, the process of field division in the process of determining the field label of the corresponding person according to the pre-processed scientific research result data includes: obtaining a number of scientific research result data corresponding to each of the fields in turn, counting the frequency of words of another single field appearing in each scientific research result data corresponding to a single field, and when the frequency is greater than the preset frequency F, determining that the single field is related to another single field, and dividing the scientific research data results of another single field into the scientific research data results of a single field, wherein the preset frequency F=16 in this embodiment.

[0037] Please continue reading Figure 4 As shown, the process of checking whether the data information is repeated in the embodiment of the present invention includes: When the verification result shows that the data information is duplicated, the data information is screened out again, and the personnel portrait information is reconstructed; When the verification result shows that there is no duplicate data information, it is determined that the quantity of the scientific research achievement data does not meet the standards, and a notice is issued to increase the quantity of scientific research achievement data to be obtained.

[0038] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0039] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0040] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for intelligently generating personnel portrait information based on multiple angles, characterized in that: include: Obtain data information of several people in the training set, including personal data and scientific research results data; Preprocessing the data information to filter out redundant data; Determine the field label of the corresponding person according to the preprocessed scientific research achievement data; For a single person, the data information is checked to determine the classification of the field label; Determining the domain weight of each of the domain labels; Constructing personnel profile information of personnel based on the weights of each of the aforementioned fields; Comparing the personnel portrait information with the preset personnel portrait information in the training set; Making a determination on the construction of the personnel portrait information based on the comparison result; Generate corresponding processing instructions based on the judgment results, Or, completing the construction of the personnel portrait information; Wherein, the determination includes determining whether the construction of the personnel portrait information is qualified and determining the reasons for failure; The operating parameters in the personnel portrait information construction process are re-determined based on the received processing instructions.

2. The method for intelligently generating personnel portrait information based on multiple angles according to claim 1 is characterized in that: The process of determining the construction of the personnel portrait information based on the comparison results includes: Determine the number of domain tags that match the domain tags in the personnel portrait information with the preset domain tags in the preset personnel portrait information, and record the obtained number as the total number of domain tag matches; Counting the number of the preset domain tags, and recording the obtained number as the total number of preset domain tags; Calculating the ratio of the total number of domain label matches to the total number of preset domain labels, and recording the obtained ratio as the domain label matching degree; When the domain label matching degree is greater than the second preset domain label matching degree, determining that the determination of the domain label is qualified, and determining whether the determination of the domain weight of each domain label is qualified; When the domain label matching degree is less than or equal to the second preset domain label matching degree and greater than the first preset domain label matching degree, determining that the determination of the domain label is unqualified, and determining whether the determination of the domain label is qualified based on the number of domain labels; When the domain label matching degree is less than or equal to the first preset domain label matching degree, it is determined that the determination of the domain label is unqualified, and the reason for the unqualified determination of the domain label is determined based on the domain label matching degree.

3. The method for intelligently generating personnel portrait information based on multiple angles according to claim 2 is characterized in that: The process of determining whether the domain weight of each domain label is qualified includes: Calculating the ratio of each of the field weights to the corresponding each of the preset field weights, and recording the obtained ratio as the field weight ratio; For each of the domain weights, the absolute value of the difference between the domain weight ratio and the domain weight standard is calculated, and the obtained absolute value is recorded as the domain weight error; Completing the calculation of the domain weight error of each of the domain weights in sequence; When the domain weight error is less than the preset domain weight error, determining that the domain weight corresponding to the domain weight error matches the preset domain weight; Based on the matching situation, it is determined whether the determination of the field weight of each field label is qualified.

4. The method for intelligently generating personnel portrait information based on multiple angles according to claim 3 is characterized in that: The process of determining whether the domain weight of each domain tag is qualified based on the matching situation includes: Recording the matched domain weight and the preset domain weight as a matching domain label group; Counting the number of matching domain label groups, and recording the obtained number as the number of matching label groups; Determine the number of the domain weights compared with the domain weight errors and the preset domain weights, and record the obtained number as the number of label groups; Calculating the ratio of the number of matching tag groups to the number of tag groups, and recording the obtained ratio as the tag group matching ratio; Determining whether the determination of the field weight of each field tag is qualified based on the tag group matching ratio; When the tag group matching ratio is greater than the preset tag group matching ratio, it is determined that the determination of the field weight of each field tag is qualified, and the construction of the personnel portrait information is completed; When the tag group matching ratio is less than or equal to the preset tag group matching ratio, it is determined that the determination of the field weight of each field label is unqualified, the preprocessing of the data information does not meet the standard, and the duplicate checking standard in the preprocessing process is corrected based on the tag group matching ratio.

5. The method for intelligently generating personnel portrait information based on multiple angles according to claim 4 is characterized in that: The process of correcting the duplicate checking standard in the preprocessing process based on the tag group matching ratio includes: Calculating the difference between the preset tag group matching ratio and the tag group matching ratio, and recording the obtained difference as the tag group matching difference; The duplicate checking standard is increased based on the tag group matching difference, and the increase in the duplicate checking standard is proportional to the tag group matching difference.

6. The method for intelligently generating personnel portrait information based on multiple angles according to claim 2 is characterized in that: The process of determining whether the determination of the domain tags is qualified based on the number of the domain tags includes: Determine the number of the domain labels, and record the obtained number as the number of domain labels; Determining whether the determination of the field label is qualified based on the number of field labels; When the number of the field tags is less than or equal to the preset number of field tags, determining that the field tags are qualified, and determining the field weights of the classified field tags; When the number of domain tags is greater than the preset number of domain tags, it is determined that the determination of the domain tags is unqualified, and the reason why the determination of the domain tags is unqualified is determined based on the domain tag matching degree.

7. The method for intelligently generating personnel portrait information based on multiple angles according to claim 2 is characterized in that: The process of determining the reason why the determination of the domain label is unqualified based on the domain label matching degree includes: Calculating the difference between the second preset domain label matching degree and the domain label matching degree, and recording the obtained difference as the label matching degree difference; Determining the reason why the determination of the field label is unqualified based on the label matching difference; When the label matching difference is less than the preset label matching difference, it is determined that the reason for the determination of the field label is unqualified is that the field division in the process of determining the field label of the corresponding person according to the preprocessed scientific research achievement data does not meet the standard, and the field division is corrected based on the label matching difference; When the tag matching difference is greater than or equal to the preset tag matching difference, it is determined that the reason for the determination of the field tag failure is that the data information does not meet the standard, and whether the data information is repeated is checked.

8. The method for intelligently generating personnel portrait information based on multiple angles according to claim 7 is characterized in that: The process of correcting the domain division based on the tag matching difference includes: Determining the preset frequency in the process of said field division; Calculating the ratio of the tag matching difference to a preset tag matching difference, and recording the obtained ratio as the tag matching ratio; The preset frequency is reduced based on the tag matching ratio, and the reduction range of the preset frequency is proportional to the tag matching ratio.

9. The method for intelligently generating personnel portrait information based on multiple angles according to claim 7 is characterized in that: The process of verifying whether the data information is repeated includes: When the verification result shows that the data information is duplicated, the data information is re-screened and the personnel portrait information is reconstructed; When the verification result shows that there is no duplicate data information, it is determined that the quantity of the scientific research achievement data does not meet the standards, and a notice is issued to increase the quantity of scientific research achievement data to be obtained.

10. A multi-angle-based intelligent generation system for personnel portrait information using the method described in any one of claims 1 to 9, characterized in that: include: A data acquisition unit, used to acquire data information of several people in the training set, including personal data and scientific research results data; A preprocessing unit, connected to the data acquisition unit, for preprocessing the data information to filter out redundant data; A domain extraction unit, which is connected to the preprocessing unit and is used to determine the domain label of the corresponding person according to the preprocessed scientific research achievement data; A label checking unit, which is connected to the field extraction unit and is used for checking the data information for a single person to determine the classification of the field label; A weight generating unit, connected to the label checking unit, for determining the domain weight of each of the domain labels; A portrait construction unit, which is connected to the weight generation unit and is used to construct personnel portrait information of personnel based on the weights of each field; An analysis unit connected to the portrait construction unit, used to compare the personnel portrait information with the preset personnel portrait information in the training set; the analysis unit is also used to make a determination on the construction of the personnel portrait information based on the comparison result; the analysis unit is also used to generate a corresponding processing instruction based on the determination result, or complete the construction of the personnel portrait information; wherein the determination includes determining whether the construction of the personnel portrait information is qualified and determining the reason for failure; A control unit, which is respectively connected to the preprocessing unit, the field extraction unit, the label checking unit and the analysis unit, and is used to redetermine the operating parameters in the process of constructing the personnel portrait information based on the received processing instructions.

Images