A lawyer recommendation matching method and computer program product

Abstract

The application discloses a lawyer recommendation matching method and a computer program product. The method comprises the following steps: S1, obtaining complaint information of a user, extracting key feature information from the complaint information, and generating a corresponding right protection case clue according to the key feature information; S2, obtaining business information of each lawyer in a lawyer library; S3, for each lawyer, calculating a field matching degree, a region matching degree and a historical case key feature information similarity of the lawyer according to the business information of the lawyer and the key feature information of the user complaint information; S4, calculating a matching score of each lawyer according to the field matching degree, the region matching degree and the historical case key feature information similarity of the lawyer; and S5, taking a lawyer with the highest matching score as a recommended lawyer, and pushing the right protection case clue corresponding to the user complaint information to the recommended lawyer. The application can recommend a lawyer more meeting the needs of a user by comprehensively considering the field matching degree, the region matching degree and the historical case key feature information similarity.

Description

Technical Field

[0001] This invention relates to the field of internet complaint service technology, and in particular to a lawyer recommendation and matching method and a computer program product. Background Technology

[0002] With the diversification of the consumer market, various consumer complaints and civil rights protection demands are also increasing. Many users whose rights have been infringed upon lack knowledge of the rights protection procedures and cannot find suitable lawyers, making it difficult to legally and reasonably safeguard their rights. Currently, some rights protection service platforms recommend lawyers based solely on the single criterion of the case type, which may not be suitable for the user's needs. Summary of the Invention

[0003] The purpose of this invention is to provide a lawyer recommendation and matching method and a computer program product that can implement the method, which can recommend suitable lawyers to users by integrating multiple indicators.

[0004] To achieve the above objectives, the present invention provides a lawyer recommendation and matching method, comprising the following steps: S1. Obtain user complaint information, extract key feature information from it and generate corresponding rights protection case clues accordingly. Key feature information includes the industry sector of the dispute, the location of the dispute, the amount involved, the details of the dispute and the rights protection claims. S2. Obtain the business information of each lawyer in the lawyer database, including their areas of expertise, work location, number of historical cases, and key characteristics. S3. For each lawyer, based on their business information and the key feature information of the aforementioned user complaint information, calculate the lawyer's domain matching degree, regional matching degree, and similarity of key feature information of historical cases; S4. Calculate the matching score for each lawyer based on their domain matching degree, regional matching degree, and similarity to key feature information of historical cases. The matching score is positively correlated with the domain matching degree, regional matching degree, and similarity to key feature information of historical cases. S5. Select the lawyer with the highest matching score as the recommended lawyer and push the rights protection case clues corresponding to the above user complaint information to that lawyer.

[0005] Furthermore: In step S2, the business information includes the number of cases being processed; In step S4, the matching score is also calculated based on the number of cases currently being handled by the lawyer, and the matching score is negatively correlated with the number of cases being handled.

[0006] Furthermore, in step S4, the matching score is also calculated based on the number of historical cases handled by the lawyer, and the matching score is positively correlated with the number of historical cases handled.

[0007] Furthermore, in step S4, the matching score is calculated according to the following formula:

[0008] Where W1 to W5 are weight coefficients, F is the domain matching degree, R is the geographic matching degree, and K is the similarity of key feature information of historical cases. The number of cases in progress. This refers to the number of historical cases.

[0009] Furthermore, in step S3: The domain matching degree is calculated as follows: if the industry field to which the dispute belongs is an industry field that the lawyer is good at, the domain matching degree is 1; otherwise, it is 0. The method for calculating the regional matching degree is as follows: calculate the distance between the location of the dispute and the location of the lawyer's work, and determine the regional matching degree based on this distance. The greater the distance, the lower the regional matching degree. The method for calculating the similarity of key feature information in historical cases is as follows: For each historical case of a lawyer, its key feature information is compared with the key feature information of the aforementioned user complaint information to determine the similarity between the two; from all the key feature information similarities of historical cases, the one with the highest similarity is taken as the key feature information similarity of the lawyer's historical cases.

[0010] Furthermore, including step S6 executed after step S5: if the lawyer does not comment on the above-mentioned rights protection case clues for more than a first preset time period, the above-mentioned rights protection case clues are withdrawn from the lawyer and instead pushed to the next lawyer whose matching score is only lower than that lawyer.

[0011] Furthermore, including step S7 executed after step S5: if a user does not reply to a lawyer after the lawyer comments on the pushed rights protection case clue, the rights protection case clue is withdrawn from the lawyer and instead pushed to the next lawyer whose matching score is only lower than that lawyer.

[0012] Furthermore, including step S8 executed after steps S6 and S7. If the user replies to the lawyer's comment, the lawyer is prompted to confirm whether to accept the case. If the lawyer confirms the case within the third preset time period, the case is marked as accepted. Otherwise, the case is withdrawn from the lawyer and pushed to the next lawyer whose matching score is only lower than the lawyer's, until a lawyer accepts the case.

[0013] Furthermore, in step S8, after the lawyer confirms acceptance of the order, an instant messaging channel is established between the lawyer and the aforementioned user.

[0014] The present invention also provides a computer program product, including a computer program that, when executed, implements the lawyer recommendation matching method as described above.

[0015] The lawyer recommendation and matching method provided in this invention calculates a matching score for each lawyer based on their domain matching degree, regional matching degree, and similarity of key feature information of historical cases in step S4. Step S5 selects the lawyer with the highest matching score as the recommended lawyer and pushes the rights protection case clues corresponding to the user complaint information to that lawyer. By combining the three indicators of domain matching degree, regional matching degree, and similarity of key feature information of historical cases, the method can recommend lawyers that better meet the user's needs. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the lawyer recommendation and matching method provided in this invention. Detailed Implementation

[0017] The present invention will be further described in detail below with reference to specific embodiments.

[0018] In this embodiment, a computer program product (hereinafter referred to as the lawyer service platform) is obtained by technicians through computer code programming. This computer program product includes a computer program, which is executed by a computer processor to achieve the following: Figure 1 The lawyer recommendation matching method is shown below. The steps of this method are detailed below.

[0019] S1. Obtain user complaint information and extract key feature information from it. Key feature information includes the industry sector of the dispute, the location of the dispute, the amount involved, the details of the dispute, and the rights protection claims.

[0020] If a user has a dispute with a merchant after making a purchase, and communication with the merchant proves ineffective, the user can file a complaint on the legal service platform described in this embodiment. Upon receiving the complaint, the platform uses an artificial intelligence model to perform structured analysis of the complaint information, automatically extracting key feature information. Then, based on this key feature information, it generates leads for a rights protection case. The key feature information includes the industry sector of the dispute, the location of the dispute, the amount involved, the details of the dispute, and the rights protection claims.

[0021] S2. Obtain the business information of each lawyer in the lawyer database, including their areas of expertise, work location, number of historical cases, and key characteristics.

[0022] After generating leads for rights protection cases, the legal service platform obtains the business information of lawyers in its database and then recommends and matches lawyers accordingly. Business information includes areas of expertise, work location, number of past cases, and key characteristics.

[0023] S3. For each lawyer, based on their business information and the key feature information of the aforementioned user complaint information, calculate the lawyer's domain matching degree, regional matching degree, and similarity of key feature information of historical cases.

[0024] After obtaining the business information of each lawyer, the legal service platform calculates the domain matching degree, geographical matching degree, and similarity of key feature information of historical cases between each lawyer and the aforementioned user complaint information, based on the business information and the key feature information of the aforementioned user complaint information. The specific calculation method is as follows: The domain matching degree is calculated as follows: The legal service platform obtains the industry domain to which the dispute belongs and compares it with the industry domain in which the lawyer is good at. It determines whether the industry domain to which the dispute belongs belongs to the industry domain in which the lawyer is good at. If the industry domain to which the dispute belongs belongs to the industry domain in which the lawyer is good at, the domain matching degree is 1; otherwise, it is 0.

[0025] The location matching degree is calculated as follows: the lawyer service platform calculates the distance between the location of the dispute and the lawyer's workplace, and determines the location matching degree based on this distance; the greater the distance, the lower the location matching degree. This embodiment pre-divides multiple distance levels, assigning a corresponding location matching degree to each distance level, and constructs a distance level-location matching degree list accordingly. After calculating the distance between the location of the dispute and the lawyer's workplace, the lawyer service platform queries the distance level-location matching degree list to determine the distance level to which that distance belongs, and thus determines the location matching degree.

[0026] The calculation method for the similarity of key feature information of historical cases is as follows: The lawyer service platform obtains the key feature information of each of the lawyer's historical cases, compares the key feature information of each of the lawyer's historical cases with the key feature information of the aforementioned user complaint information, and determines the similarity between the two; then, from all the key feature information similarities of historical cases, the one with the highest similarity is taken as the key feature information similarity of the lawyer's historical cases.

[0027] S4. Calculate the matching score for each lawyer based on their domain matching degree, regional matching degree, and similarity of key feature information of historical cases.

[0028] The legal service platform calculates a matching score for each lawyer based on their domain matching degree, regional matching degree, and similarity to key features of historical cases. The matching score is positively correlated with the domain matching degree, regional matching degree, and similarity to key features of historical cases.

[0029] In other embodiments, the aforementioned business information includes the number of cases being processed. The matching score is also calculated based on the number of cases currently being processed by the lawyer and the number of historical cases. The matching score is negatively correlated with the number of cases being processed and positively correlated with the number of historical cases. Specifically, the matching score (Score) is calculated according to the following formula:

[0030] Where W1 to W5 are weight coefficients, F is the domain matching degree, R is the geographic matching degree, and K is the similarity of key feature information of historical cases. The number of cases in progress. This refers to the number of historical cases.

[0031] S5. Select the lawyer with the highest matching score as the recommended lawyer and push the rights protection case clues corresponding to the above users' complaint information to that lawyer.

[0032] The legal service platform sorts all lawyers from highest to lowest according to their matching scores, and recommends the lawyer with the highest matching score, pushing the rights protection case clues corresponding to the user's complaint information to that lawyer.

[0033] S6. If the lawyer does not comment on the above-mentioned rights protection case clues within the first preset time period, the above-mentioned rights protection case clues will be withdrawn from the lawyer and instead pushed to the next lawyer whose matching score is only lower than that lawyer.

[0034] After receiving a lead on a rights protection case, a lawyer can provide a professional assessment and commentary based on their expertise and available time. After the lawyer service platform pushes the case lead to a lawyer, it monitors whether the lawyer comments on it. If the lawyer fails to comment on the case lead within a preset timeframe, such as more than 6 hours, the case lead is withdrawn from that lawyer and forwarded to the next lawyer with a matching score only lower than that lawyer.

[0035] S7. If a user does not reply to a lawyer after the lawyer comments on the pushed rights protection case clue, the case clue will be withdrawn from the lawyer and pushed to the next lawyer whose matching score is only lower than the lawyer's.

[0036] If a lawyer comments on a submitted legal aid case lead, the legal service platform notifies the user via SMS and push notification, and monitors whether the user responds to the lawyer. If the platform detects that the user has not responded to the lawyer for more than a second preset time period, such as more than 120 hours, it means that the lawyer's comment has not aroused the user's interest. The platform then withdraws the legal aid case lead from that lawyer and forwards it to the next lawyer with a matching score only lower than that lawyer.

[0037] S8. If a user replies to a lawyer's comment, the lawyer will be prompted to confirm whether to accept the case. If the lawyer confirms the case within the third preset time period, the case will be marked as accepted. Otherwise, the case will be withdrawn from the lawyer and pushed to the next lawyer whose matching score is only lower than the lawyer's, until a lawyer accepts the case.

[0038] If the legal service platform detects that a user has responded to a lawyer's comment within a second preset time period, it will prompt the lawyer to confirm acceptance of the case. If the lawyer confirms acceptance within a third preset time period, such as within 30 hours, the case lead will be marked as accepted. Otherwise, the case lead will be withdrawn from the lawyer's office and pushed to the next lawyer with a matching score only lower than the current lawyer, until a lawyer accepts the case lead. After the lawyer confirms acceptance, the legal service platform will establish an instant messaging channel between the lawyer and the user to facilitate communication regarding the complaint and solutions.

[0039] The lawyer recommendation and matching method provided in this invention calculates a matching score for each lawyer based on their domain matching degree, regional matching degree, and similarity of key feature information of historical cases in step S4. Step S5 selects the lawyer with the highest matching score as the recommended lawyer and pushes the rights protection case clues corresponding to the user complaint information to that lawyer. By combining the three indicators of domain matching degree, regional matching degree, and similarity of key feature information of historical cases, the method can recommend lawyers that better meet the user's needs.

[0040] The above description is merely an embodiment of the present invention and does not limit the scope of patent protection. Any non-substantial changes or substitutions made by those skilled in the art based on the present invention will still fall within the scope of patent protection.

Claims

1. A lawyer recommendation and matching method, characterized in that, Includes the following steps: S1. Obtain user complaint information, extract key feature information from it and generate corresponding rights protection case clues accordingly. Key feature information includes the industry sector of the dispute, the location of the dispute, the amount involved, the details of the dispute and the rights protection claims. S2. Obtain the business information of each lawyer in the lawyer database, including their areas of expertise, work location, number of historical cases, and key characteristics. S3. For each lawyer, based on their business information and the key feature information of the aforementioned user complaint information, calculate the lawyer's domain matching degree, regional matching degree, and similarity of key feature information of historical cases; S4. Calculate the matching score for each lawyer based on their domain matching degree, regional matching degree, and similarity to key feature information of historical cases. The matching score is positively correlated with the domain matching degree, regional matching degree, and similarity to key feature information of historical cases. S5. Select the lawyer with the highest matching score as the recommended lawyer and push the rights protection case clues corresponding to the above user complaint information to that lawyer.

2. The lawyer recommendation and matching method as described in claim 1, characterized in that: In step S2, the business information includes the number of cases being processed; In step S4, the matching score is also calculated based on the number of cases currently being handled by the lawyer, and the matching score is negatively correlated with the number of cases being handled.

3. The lawyer recommendation and matching method as described in claim 2, characterized in that, In step S4, the matching score is also calculated based on the number of historical cases handled by the lawyer, and the matching score is positively correlated with the number of historical cases handled.

4. The lawyer recommendation and matching method as described in claim 3, characterized in that, In step S4, the matching score is calculated according to the following formula: Where W1 to W5 are weight coefficients, F is the domain matching degree, R is the geographic matching degree, and K is the similarity of key feature information of historical cases. The number of cases in progress. This refers to the number of historical cases.

5. The lawyer recommendation and matching method as described in claim 1, characterized in that, In step S3: The domain matching degree is calculated as follows: if the industry field to which the dispute belongs is an industry field that the lawyer is good at, the domain matching degree is 1; otherwise, it is 0. The method for calculating the regional matching degree is as follows: calculate the distance between the location of the dispute and the location of the lawyer's work, and determine the regional matching degree based on this distance. The greater the distance, the lower the regional matching degree. The method for calculating the similarity of key feature information in historical cases is as follows: For each historical case of a lawyer, its key feature information is compared with the key feature information of the aforementioned user complaint information to determine the similarity between the two; from all the key feature information similarities of historical cases, the one with the highest similarity is taken as the key feature information similarity of the lawyer's historical cases.

6. The lawyer recommendation and matching method as described in claim 1, characterized in that, This includes step S6, which is executed after step S5. If the lawyer does not comment on the above-mentioned rights protection case clues within a first preset time period, the above-mentioned rights protection case clues are withdrawn from the lawyer and instead pushed to the next lawyer whose matching score is only lower than that lawyer.

7. The lawyer recommendation and matching method as described in claim 6, characterized in that, This includes S7, which is executed after step S5. If a user does not reply to a lawyer after the lawyer comments on the pushed rights protection case clue, the rights protection case clue is withdrawn from the lawyer and pushed to the next lawyer whose matching score is only lower than that lawyer.

8. The lawyer recommendation and matching method as described in claim 7, characterized in that, This includes step S8, which is executed after steps S6 and S7. If the user replies to the lawyer's comment, the lawyer is prompted to confirm whether to accept the case. If the lawyer confirms the case within the third preset time period, the case is marked as accepted. Otherwise, the case is withdrawn from the lawyer and pushed to the next lawyer whose matching score is only lower than the lawyer's, until a lawyer accepts the case.

9. The lawyer recommendation and matching method as described in claim 8, characterized in that, In step S8, after the lawyer confirms acceptance of the order, an instant messaging channel is established between the lawyer and the aforementioned user.

10. A computer program product, characterized in that, Includes a computer program that, when executed, implements the lawyer recommendation matching method as described in any one of claims 1 to 9.

Images