A smart government service method and system based on artificial intelligence technology

Abstract

The present invention provides a smart government service method and system based on artificial intelligence technology, which belongs to the field of data management technology, and specifically includes: using text similarity coefficients to divide the proposal texts into different similar proposal combinations, determining the number of proposal texts in different similar proposal combinations, and determining the recommendation processing priority of different similar proposal combinations in combination with the text similarity coefficients between different proposal texts and the submission time of the proposal texts, and using the text similarity coefficients between the proposal texts in the similar proposal combination and other proposal texts, and the text matching coefficients with the competent authorities, using a preset AI model to determine the recommendation processing order of different proposal texts in the similar proposal combination, thereby improving the processing efficiency of the proposal texts.

Description

Technical Field

[0001] The present invention belongs to the field of data management technology, and in particular relates to a smart government service method and system based on artificial intelligence technology. Background Art

[0002] Meetings are held regularly in various regions across the country every year, during which government agencies receive a large number of proposals. Therefore, in order to achieve accurate management services for proposals, the collected public opinions are classified and reported to the public opinion processing center in the invention patent application CN202211485742.9 "A Proposal Collection System Based on Big Data Public Opinion", and then disclosed to the public in a timely manner through the government website. Anyone can query and read it, so that the public opinion processing situation can be widely supervised by the public. However, the existing technical solutions have the following technical problems:

[0003] Since there are a large number of proposal texts and the proposal texts often involve different departments, it is impossible to guarantee the processing efficiency of the proposal texts by performing differentiated push processing based on the analysis results of the proposal texts.

[0004] In response to the above technical problems, the present invention provides a smart government service method and system based on artificial intelligence technology. Summary of the invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] According to one aspect of the present invention, a smart government service method based on artificial intelligence technology is provided.

[0007] A smart government service method based on artificial intelligence technology, specifically including:

[0008] S1 parses the proposal text to obtain a parsing result, uses the parsing result to determine the matching status of the proposal text with different institutions, and when it is determined that the proposal text has a competent institution based on the matching status with different institutions, determines the text matching coefficient between the proposal text and the competent institution, and proceeds to the next step;

[0009] S2 divides the proposal texts into different combinations based on the competent authority, determines text similarity coefficients of different proposal texts based on the parsing results of the proposal texts in different combinations, and divides the proposal texts into different similar proposal combinations using the text similarity coefficients;

[0010] S3 determines the number of proposal texts in different similar proposal combinations, and determines the recommendation processing priorities of different similar proposal combinations based on the text similarity coefficients between the different proposal texts and the submission time of the proposal texts;

[0011] S4 uses a preset AI model to determine the recommended processing order of different proposal texts in the similar proposal combination based on the text similarity coefficient between the proposal text in the similar proposal combination and other proposal texts and the text matching coefficient with the competent authority.

[0012] The beneficial effects of the present invention are:

[0013] 1. The recommended processing priority of different similar proposal combinations is determined based on the number of proposal texts in different similar proposal combinations, the text similarity coefficients between different proposal texts, and the submission time of the proposal texts. This takes into account the differences in processing requirements caused by the number of proposal texts in similar proposal combinations and the differences in submission time, as well as the differences in processing difficulty of proposal texts in similar proposal combinations caused by the text similarity coefficients between the proposal texts in similar proposal combinations. This enables timely processing of similar proposal combinations with lower processing difficulty and larger number, thereby improving the processing efficiency of proposals.

[0014] 2. The recommended processing order of different proposal texts in a similar proposal combination is determined based on the text similarity coefficient between the proposal text and other proposal texts and the text matching coefficient with the competent authority. This not only ensures the processing efficiency of proposal texts with a high degree of similarity with other proposal texts in the similar proposal combination, but also ensures the processing efficiency of proposal texts with a high text matching coefficient with the competent authority, further improving the timeliness and accuracy of the processing of proposal texts by the competent authority.

[0015] A further technical solution is that the analysis result includes the number of problems in the proposal text and suggestions for handling different problems.

[0016] A further technical solution is that the matching of the proposal text with different institutions includes the matching coefficients of different problems in the proposal text with different institutions and the matching coefficients of treatment suggestions for the problems with different institutions.

[0017] A further technical solution is that the matching coefficient between the question and different institutions is determined according to the matching between the business type corresponding to the question and the business type of the institution.

[0018] A further technical solution is to determine whether the proposal text has a competent authority, including:

[0019] Based on the matching conditions with different institutions, the matching coefficients between different issues in the proposal text and different institutions are determined, and the weights and sums of the matching coefficients between the proposal text and different institutions are determined in combination with the treatment suggestions for different issues and the matching coefficients of different institutions;

[0020] Determine the candidate competent authority among the institutions based on the sum of the weights of the matching coefficients between the proposal text and different institutions, and determine the significance of the matching coefficient of the candidate competent authority using the deviation of the sum of the weights of the matching coefficients between the candidate competent authority and other institutions;

[0021] It is determined whether there is a competent authority for the proposal text based on the significance of the matching coefficient.

[0022] A further technical solution is that the method for determining the recommended processing order of the proposal text is:

[0023] Determining a comprehensive text similarity coefficient of the proposal text based on the text similarity coefficients between the proposal text and other proposal texts in the similar proposal combination;

[0024] Based on the comprehensive text similarity coefficient of the proposal text and the text matching coefficient with the competent authority, a preset AI model is used to determine the comprehensive matching coefficient of the proposal text, and the recommended processing order of the proposal text is determined according to the comprehensive matching coefficient.

[0025] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned smart government service method based on artificial intelligence technology.

[0026] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0027] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings;

[0029] Figure 1 It is a flow chart of a smart government service method based on artificial intelligence technology;

[0030] Figure 2 It is a flow chart of the method for determining the significance of the matching coefficient of the candidate competent authority;

[0031] Figure 3 is a flow chart of a method for determining a matching coefficient between a proposal text and a text of said competent authority;

[0032] Figure 4is a flow chart of a method for determining a text similarity coefficient of a proposal text;

[0033] Figure 5 It is a framework diagram of a computer system. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0035] Since there are a large number of proposal texts and the proposal texts often involve different departments, it is necessary to push the proposal texts to the relevant competent departments through the analysis results of the proposal texts to improve the processing efficiency of the proposal texts.

[0036] Text matching coefficient: It is determined based on the number of matches between the keywords in the proposal text and the competent authorities. Specifically, when the number of matches is 20, the corresponding preset matching coefficient is 0.5, and the text matching coefficient at this time is 0.5.

[0037] Text similarity coefficient: It is determined based on the similarity ratio of keywords between proposal texts. For example, if the number of keywords is 50 and the number of similar keywords is 20, the text similarity coefficient is 0.4.

[0038] The recommendation processing priority includes a first level and a second level, which is specifically determined based on the number of proposal texts within different submission time intervals and the matching preset recommendation processing priority. The first level is greater than the second level.

[0039] Recommended processing order: Based on the text similarity coefficient between the proposal text and other texts, and the text matching coefficient with the competent authority, a preset AI model is used to determine the comprehensive matching coefficient of the proposal text, and the recommended processing order of the proposal text is determined based on the comprehensive matching coefficient, where the value range of the comprehensive matching coefficient is between 0 and 1. The larger the comprehensive matching coefficient, the higher the recommended processing order.

[0040] The above-mentioned AI model can be constructed using any one of KNN, LSTM, CNN, RNN and BP neural networks. Example

[0041] To solve the above problems, according to one aspect of the present invention, Figure 1As shown, a smart government service method based on artificial intelligence technology is provided, which specifically includes:

[0042] S1 parses the proposal text to obtain a parsing result, uses the parsing result to determine the matching status of the proposal text with different institutions, and when it is determined that the proposal text has a competent institution based on the matching status with different institutions, determines the text matching coefficient between the proposal text and the competent institution, and proceeds to the next step;

[0043] Furthermore, the analysis result includes the number of problems in the proposal text and suggestions for handling different problems.

[0044] Specifically, the matching situation between the proposal text and different institutions includes the matching coefficients between different issues in the proposal text and different institutions and the matching coefficients between the handling suggestions for the issues and different institutions.

[0045] It can be understood that the matching coefficient between the question and different institutions is determined according to the matching between the business type corresponding to the question and the business type of the institution.

[0046] It should be noted that the competent authorities for determining the existence of the proposal text include:

[0047] Based on the matching conditions with different institutions, the matching coefficients between different issues in the proposal text and different institutions are determined, and the weights and sums of the matching coefficients between the proposal text and different institutions are determined in combination with the treatment suggestions for different issues and the matching coefficients of different institutions;

[0048] Determine the candidate competent authority among the institutions based on the sum of the weights of the matching coefficients between the proposal text and different institutions, and determine the significance of the matching coefficient of the candidate competent authority using the deviation of the sum of the weights of the matching coefficients between the candidate competent authority and other institutions;

[0049] It is determined whether there is a competent authority for the proposal text based on the significance of the matching coefficient.

[0050] Furthermore, the competent authority to be selected in the institution is the competent authority with the largest weight of matching coefficient in the institution.

[0051] Specifically, Figure 2 As shown, the method for determining the significance of the matching coefficient of the candidate competent authority is:

[0052] Determine the deviation of the weighted sum of the matching coefficients between the candidate competent authority and other institutions by using the deviation of the weighted sum of the matching coefficients between the candidate competent authority and other institutions, and determine the significant coefficient between the candidate competent authority and other institutions by using the deviation;

[0053] The significance of the matching coefficient of the candidate competent authority is determined based on the sum of the significance coefficients between the candidate competent authority and other institutions.

[0054] Furthermore, when the significance of the matching coefficient of the candidate competent authority meets the requirement, it is determined that there is a competent authority in the proposal text.

[0055] Specifically, determine whether the proposal text exists in a competent authority, including:

[0056] Based on the matching conditions with different institutions, the matching coefficients between different issues in the proposal text and different institutions are determined, and the weights and sums of the matching coefficients between the proposal text and different institutions are determined in combination with the treatment suggestions for different issues and the matching coefficients of different institutions;

[0057] It is determined whether there is a competent authority for the proposal text based on the deviation of the matching coefficient weights and the deviation of different institutions.

[0058] Furthermore, when the deviation of the sum of the matching coefficient weights is greater than a preset deviation threshold, it is determined that there is a competent authority in the proposal text.

[0059] It should also be noted that the competent authorities for determining the existence of the proposal text include:

[0060] S11 determines the matching coefficients between different issues in the proposal text and different institutions based on the matching conditions with different institutions, and determines the weights and sums of the matching coefficients between the proposal text and different institutions in combination with the treatment suggestions for different issues and the matching coefficients of different institutions, and judges whether there is an institution with the matching coefficient weight and sum that meets the requirements. If so, proceed to the next step; if not, it is determined that there is no competent institution in the proposal text;

[0061] S12 determines the candidate competent authority among the institutions based on the sum of the matching coefficient weights of the proposal text and different institutions, and determines whether there are other institutions whose deviation from the sum of the matching coefficient weights of the candidate competent authority is within a preset range. If so, proceed to the next step; if not, proceed to step S15;

[0062] S13: other institutions whose deviation from the weight sum of matching coefficients of the selected competent institution is within a preset range are regarded as matching similar institutions, and it is determined whether the number of the matching similar institutions meets the requirement. If so, the next step is entered; if not, it is determined that there is no competent institution in the proposal text;

[0063] S14 determines the similarity of the matching coefficients between the matching similar institutions and the competent institution to be selected by using the deviation of the weights of the matching coefficients between the different matching similar institutions and the competent institution to be selected, and judges whether the matching coefficient similarity meets the requirements. If so, proceeds to the next step; if not, determines that there is no competent institution in the proposal text;

[0064] S15 determines the significance of the matching coefficient of the candidate competent authority by using the deviation of the sum of the matching coefficient weights between the candidate competent authority and other institutions, and determines whether there is a competent authority in the proposal text based on the significance of the matching coefficient.

[0065] Specifically, Figure 3 As shown, the method for determining the matching coefficient between the proposal text and the text of the competent authority is:

[0066] Based on the matching conditions with different institutions, the matching coefficients between different issues in the proposal text and different institutions are determined, and the weights and sums of the matching coefficients between the proposal text and different institutions are determined in combination with the treatment suggestions for different issues and the matching coefficients of different institutions;

[0067] The significance of the matching coefficients of different institutions is determined by using the deviation of the matching coefficient weights and the matching coefficients between different institutions and other institutions;

[0068] The text matching coefficients between the proposal text and different institutions are determined based on the matching coefficient weights and matching coefficient significances between the proposal text and different institutions, and the competent institution of the proposal text is determined using the text matching coefficients.

[0069] Furthermore, the text matching coefficient has a value range between 0 and 1, and the institution with the largest text matching coefficient is regarded as the competent authority.

[0070] It should be further explained that the method for determining the matching coefficient between the proposal text and the text of the competent authority is as follows:

[0071] S111 determines the matching coefficients between different issues in the proposal text and different institutions based on the matching conditions with different institutions, and determines the weight sum of the matching coefficients between the proposal text and different institutions in combination with the handling suggestions for different issues and the matching coefficients of different institutions, and judges whether the weight sum of the matching coefficients between the proposal text and the institutions meets the requirements. If so, proceed to the next step; if not, determine that the institutions do not belong to the competent institutions;

[0072] S112 uses the deviation of the sum of matching coefficient weights between different institutions and other institutions to determine whether there are other institutions whose deviation of the sum of matching coefficient weights is less than the preset weight threshold. If yes, proceed to the next step; if not, proceed to step S115;

[0073] S113 determines whether there are other institutions whose deviation of the sum of the matching coefficient weights is less than the preset minimum weight value. If not, proceed to the next step. If yes, determine that the institution does not belong to the competent authority.

[0074] S114 determines whether the number of other institutions whose deviation of the weight sum of the matching coefficients is less than the preset weight threshold meets the requirement, if so, proceeds to the next step, if not, determines that the institution does not belong to the competent institution;

[0075] S115 determines the significance of the matching coefficients of different institutions by using the deviation of the weights and sums of the matching coefficients between different institutions and other institutions, and judges whether the significance of the matching coefficients of the institutions meets the requirements. If so, proceed to the next step. If not, it is determined that the institutions do not belong to the competent institutions.

[0076] S116 determines the text matching coefficient between the proposal text and different institutions based on the matching coefficient weight and matching coefficient significance between the proposal text and different institutions, and uses the text matching coefficient to determine the competent institution of the proposal text.

[0077] S2 divides the proposal texts into different combinations based on the competent authority, determines text similarity coefficients of different proposal texts based on the parsing results of the proposal texts in different combinations, and divides the proposal texts into different similar proposal combinations using the text similarity coefficients;

[0078] Specifically, Figure 4 As shown, the method for determining the text similarity coefficient of the proposal text is:

[0079] Determining a question text similarity coefficient between the proposal texts based on text similarities of different questions between the proposal texts;

[0080] Determining a suggestion text similarity coefficient between the proposal texts based on text similarities of treatment suggestions for different issues between the proposal texts;

[0081] The text similarity coefficient between the proposal texts is determined by the average value of the suggestion text similarity coefficient and the question text similarity coefficient.

[0082] Furthermore, the text similarity coefficient between the proposed texts ranges from 0 to 1, wherein the greater the text similarity coefficient between the proposed texts, the higher the degree of text similarity between the proposed texts.

[0083] It is understandable that the proposal texts are divided into different similar proposal groups, including:

[0084] The proposal texts whose text similarity coefficient is greater than the preset similarity coefficient are divided into the same similar proposal group.

[0085] S3 determines the number of proposal texts in different similar proposal combinations, and determines the recommendation processing priorities of different similar proposal combinations based on the text similarity coefficients between the different proposal texts and the submission time of the proposal texts;

[0086] Specifically, the method for determining the recommendation processing priority of the similar proposal combination is:

[0087] Determine a quantity processing priority value of the similar proposal combination based on the quantity of proposal texts of the similar proposal combination;

[0088] Determine the average value of the text similarity coefficients between different proposal texts in the similar proposal combination through the text similarity coefficients between different proposal texts, and determine the similarity processing priority value of the similar proposal combination using the average value of the text similarity coefficients between different proposal texts;

[0089] The time of submission of the proposal texts in the similar proposal combination is used to calculate the average of the interval time between the submission time of the proposal texts in the similar proposal combination and the current moment, and the time processing priority value of the similar proposal combination is determined by using the average of the interval time;

[0090] The comprehensive processing priority value of the similar proposal combination is determined based on the time processing priority value, quantity processing priority value and the average value of the similar processing priority value of the similar proposal combination, and the recommended processing priority of the similar proposal combination is determined using the processing priority corresponding to the comprehensive processing priority value.

[0091] Furthermore, the quantity processing priority value of the similar proposal combination is determined according to the product of the quantity of proposal texts of the similar proposal combination and a preset proportional factor.

[0092] It should be further explained that the method for determining the recommendation processing priority of the similar proposal combination is:

[0093] Determine the interval between the submission time and the current time based on the submission time of the proposal text of the similar proposal combination, and use the interval between the submission time and the current time to determine the time processing requirement values ​​of different submission texts;

[0094] Determine text processing requirement values ​​of different submitted texts by averaging text similarity coefficients between different proposal texts in the similar proposal combination and other proposal texts in the similar proposal combination;

[0095] The priority processing coefficients of different submitted texts are determined based on the average values ​​of the text processing requirement values ​​and time processing priority values ​​of different submitted texts, and the comprehensive processing priority value of the similar proposal combination is determined in combination with the number of submitted texts in the similar proposal combination, and the recommended processing priority of the similar proposal combination is determined using the processing priority corresponding to the comprehensive processing priority value.

[0096] It should be further explained that the method for determining the recommendation processing priority of the similar proposal combination is:

[0097] S31 obtains the number of proposal texts of the similar proposal combination, and determines whether the number of submitted texts of the similar proposal combination is greater than a preset number of texts. If so, proceeds to the next step; if not, proceeds to step S34;

[0098] S32 determines the interval between the submission time and the current time through the submission time of the proposal texts in the similar proposal combination, and judges whether the number of submitted texts with an interval time longer than the preset time is greater than a preset number threshold. If so, the recommendation processing priority of the similar proposal combination is set to the first level. If not, proceed to the next step.

[0099] S33 determines the number of proposal texts whose text similarity coefficients are greater than a preset coefficient threshold value through the text similarity coefficients between different proposal texts in the similar proposal combination, and judges whether the number of proposal texts whose text similarity coefficients are greater than the preset coefficient threshold value is greater than the preset number threshold value, if so, sets the recommendation processing priority of the similar proposal combination to the first level, if not, proceeds to the next step;

[0100] S34 determines the time processing requirement values ​​of different submitted texts by using the interval between the submission time and the current time, and determines the text processing requirement values ​​of different submitted texts by using the average value of the text similarity coefficients of different proposal texts in the similar proposal combination and other proposal texts in the similar proposal combination;

[0101] S35 determines the text processing requirement values ​​of different submitted texts by the average value of the text similarity coefficients between different proposal texts in the similar proposal combination and other proposal texts in the similar proposal combination, and judges whether the number of submitted texts whose text processing requirement values ​​are greater than a preset requirement threshold is greater than a preset number threshold. If so, sets the recommended processing priority of the similar proposal combination to the first level; if not, proceeds to the next step;

[0102] S36 determines the priority processing coefficients of different submitted texts based on the average values ​​of the text processing requirement values ​​and time processing priority values ​​of different submitted texts, determines the comprehensive processing priority value of the similar proposal combination in combination with the number of submitted texts in the similar proposal combination, and determines the recommended processing priority of the similar proposal combination using the processing priority corresponding to the comprehensive processing priority value.

[0103] S4 uses a preset AI model to determine the recommended processing order of different proposal texts in the similar proposal combination based on the text similarity coefficient between the proposal text in the similar proposal combination and other proposal texts and the text matching coefficient with the competent authority.

[0104] Specifically, the method for determining the recommended processing order of the proposal text is:

[0105] Determining a comprehensive text similarity coefficient of the proposal text based on the text similarity coefficients between the proposal text and other proposal texts in the similar proposal combination;

[0106] Based on the comprehensive text similarity coefficient of the proposal text and the text matching coefficient with the competent authority, a preset AI model is used to determine the comprehensive matching coefficient of the proposal text, and the recommended processing order of the proposal text is determined according to the comprehensive matching coefficient. Example

[0107] Second, as Figure 5 As shown, the present invention provides a computer system, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned smart government service method based on artificial intelligence technology.

[0108] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0109] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0110] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A smart government service method based on artificial intelligence technology, characterized in that: Specifically include: The proposal text is parsed to obtain a parsing result, and the parsing result is used to determine the matching status of the proposal text with different institutions. When it is determined that the proposal text has a competent institution based on the matching status with different institutions, the text matching coefficient between the proposal text and the competent institution is determined, and the next step is entered; Based on the competent authority, the proposal texts are divided into different combinations, text similarity coefficients of different proposal texts are determined based on the parsing results of the proposal texts in different combinations, and the proposal texts are divided into different similar proposal combinations using the text similarity coefficients; Determine the number of proposal texts in different similar proposal combinations, and determine the priority of recommended processing of different similar proposal combinations based on the text similarity coefficients between different proposal texts and the submission time of the proposal texts; Determine the recommended processing order of different proposal texts in the similar proposal combination using a preset AI model based on the text similarity coefficient between the proposal text in the similar proposal combination and other proposal texts and the text matching coefficient with the competent authority; Determine the existence of the competent authority for the proposed text, including: S11 determines the matching coefficients between different issues in the proposal text and different institutions based on the matching conditions with different institutions, and determines the weights and sums of the matching coefficients between the proposal text and different institutions in combination with the treatment suggestions for different issues and the matching coefficients of different institutions, and judges whether there is an institution with the matching coefficient weight and sum that meets the requirements. If so, proceed to the next step; if not, it is determined that there is no competent institution in the proposal text; S12 determines the candidate competent authority among the institutions based on the sum of the matching coefficient weights of the proposal text and different institutions, and determines whether there are other institutions whose deviation from the sum of the matching coefficient weights of the candidate competent authority is within a preset range. If so, proceed to the next step; if not, proceed to step S15; S13: other institutions whose deviation from the weight sum of matching coefficients of the selected competent institution is within a preset range are regarded as matching similar institutions, and it is determined whether the number of the matching similar institutions meets the requirement. If so, the next step is entered; if not, it is determined that there is no competent institution in the proposal text; S14 determines the similarity of the matching coefficients between the matching similar institutions and the competent institution to be selected by using the deviation of the weights of the matching coefficients between the different matching similar institutions and the competent institution to be selected, and judges whether the matching coefficient similarity meets the requirements. If so, proceeds to the next step; if not, determines that there is no competent institution in the proposal text; S15 determines the significance of the matching coefficient of the candidate competent authority by using the deviation of the weight sum of the matching coefficients of the candidate competent authority and other institutions, and determines whether there is a competent authority in the proposal text based on the significance of the matching coefficient; The method for determining the recommendation processing priority of the similar proposal combination is: S31 obtains the number of proposal texts of the similar proposal combination, and determines whether the number of submitted texts of the similar proposal combination is greater than a preset number of texts. If so, proceeds to the next step; if not, proceeds to step S34; S32 determines the interval between the submission time and the current time through the submission time of the proposal texts in the similar proposal combination, and judges whether the number of submitted texts with an interval time longer than the preset time is greater than a preset number threshold. If so, the recommendation processing priority of the similar proposal combination is set to the first level. If not, proceed to the next step. S33 determines the number of proposal texts whose text similarity coefficients are greater than a preset coefficient threshold value through the text similarity coefficients between different proposal texts in the similar proposal combination, and judges whether the number of proposal texts whose text similarity coefficients are greater than the preset coefficient threshold value is greater than the preset number threshold value, if so, sets the recommendation processing priority of the similar proposal combination to the first level, if not, proceeds to the next step; S34 determines the time processing requirement values ​​of different submitted texts by using the interval between the submission time and the current time, and determines the text processing requirement values ​​of different submitted texts by using the average value of the text similarity coefficients of different proposal texts in the similar proposal combination and other proposal texts in the similar proposal combination; S35 determines the text processing requirement values ​​of different submitted texts by the average value of the text similarity coefficients between different proposal texts in the similar proposal combination and other proposal texts in the similar proposal combination, and judges whether the number of submitted texts whose text processing requirement values ​​are greater than a preset requirement threshold is greater than a preset number threshold. If so, sets the recommended processing priority of the similar proposal combination to the first level; if not, proceeds to the next step; S36 determines the priority processing coefficients of different submitted texts based on the average values ​​of the text processing requirement values ​​and time processing priority values ​​of different submitted texts, determines the comprehensive processing priority value of the similar proposal combination in combination with the number of submitted texts in the similar proposal combination, and determines the recommended processing priority of the similar proposal combination using the processing priority corresponding to the comprehensive processing priority value.

2. The smart government service method based on artificial intelligence technology as claimed in claim 1, characterized in that: The analysis result includes the number of problems in the proposal text and suggestions for handling different problems.

3. The smart government service method based on artificial intelligence technology as claimed in claim 1, characterized in that: The method for determining the recommended processing order of the proposal text is: Determining a comprehensive text similarity coefficient of the proposal text based on the text similarity coefficients between the proposal text and other proposal texts in the similar proposal combination; Based on the comprehensive text similarity coefficient of the proposal text and the text matching coefficient with the competent authority, a preset AI model is used to determine the comprehensive matching coefficient of the proposal text, and the recommended processing order of the proposal text is determined according to the comprehensive matching coefficient.

4. A computer system comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, an intelligent government service method based on artificial intelligence technology as described in any one of claims 1-3 is executed.

Images