Case recommendation method, device and equipment for surveyors and storage medium

Abstract

The invention discloses a surveyor case recommendation method, apparatus and device, and a storage medium, through feature extraction of historical cases, including interaction information of surveyors and related parties of the historical cases in a case processing process, construction of a collaborative filtering model, and recommendation of new cases based on the collaborative filtering model, recommendation results are more accurate, and the recommendation efficiency is improved. Meanwhile, real-time communication and cooperative work of the cases can be conveniently carried out based on the IM communication technology, the working efficiency and service quality of surveyors are improved, and the technical problems that a traditional case survey and recommendation method mainly depends on artificial experience and knowledge and is low in efficiency and accuracy are solved.

Description

Technical Field

[0001] The present application relates to the field of recommendation technology, and in particular to a method, device, equipment and storage medium for recommending cases to surveyors. Background Art

[0002] With the rapid development of Internet technology, users' demand for case recommendations for investigators is growing. Although traditional recommendation algorithms can meet users' basic needs to a certain extent, they mainly rely on users' historical behaviors and preferences. This method has certain limitations in predicting the accuracy of user needs.

[0003] Traditional recommendation algorithms usually predict cases that users may be interested in by analyzing historical behavior data such as browsing history and purchase history. However, this approach has the following major problems:

[0004] Strong data dependence: The effectiveness of the algorithm is highly dependent on the user's historical data. For new users or users with less behavior, the recommendation effect may not be good.

[0005] Static recommendation: The recommendation results are often static and cannot be adjusted according to the real-time changes in user needs.

[0006] Lack of accuracy: Reliance on a single data source fails to fully consider users’ actual needs and preferences.

[0007] During the case investigation and recommendation process, investigators need to make quick and accurate judgments and recommendations on cases in order to help the police quickly locate and handle cases, avoiding the technical problems of low efficiency and low accuracy of traditional case investigation and recommendation methods that mainly rely on manual experience and knowledge. Summary of the invention

[0008] The present application provides a method, device, equipment and storage medium for recommending cases to investigators, which solves the technical problems that traditional case investigation and recommendation methods mainly rely on manual experience and knowledge, and have low efficiency and low accuracy.

[0009] In view of this, the first aspect of the present application provides a method for recommending cases to surveyors, the method comprising:

[0010] Step S1, obtaining the conversation information between the surveyor and the parties involved in the historical case based on the IM communication technology and the relevant information on the handling of the historical case;

[0011] Step S2, extracting case interaction feature information and emotion feature information from the dialogue information;

[0012] Step S3, constructing a collaborative filtering model based on the case interaction feature information, the sentiment feature information, and the processing result information of the historical cases of the surveyor;

[0013] Step S4: Based on the collaborative filtering model, the newly input case information is analyzed to form a first recommendation list, wherein the first recommendation list contains information of several surveyors that meet the preset matching.

[0014] Optionally, the step S1 specifically includes:

[0015] When the surveyor handles a historical case, a first communication group for the historical case is established based on IM communication technology, wherein the first communication group includes the surveyor and parties related to the historical case;

[0016] Acquire the conversation information of the surveyor in the first communication group during the process of handling the historical case.

[0017] Optionally, the step S2 specifically includes:

[0018] By analyzing the conversation information, case interaction feature information including communication frequency, average communication duration, and communication time period is extracted from the conversation information;

[0019] The natural language processing technology is used to perform sentiment analysis on the dialogue information, and the sentiment feature information of the dialogue information is extracted based on the keywords contained in the dialogue information.

[0020] Optionally, the step S3 specifically includes:

[0021] The basic information of the surveyor and the case interaction feature information, the sentiment feature information and the processing related information of the historical cases are converted into a matrix form, and a collaborative filtering model including a surveyor-case matrix is ​​constructed;

[0022] The collaborative filtering model is trained by a collaborative filtering algorithm.

[0023] Optionally, the step S4 specifically includes:

[0024] Extract feature information of newly input case information;

[0025] According to the characteristic information of the newly input case information, combined with the collaborative filtering model, a first recommendation list is formed, wherein the first recommendation list contains a plurality of surveyor information that meets the preset matching.

[0026] Optionally, after step S4, the following steps are further included:

[0027] Step S5: Push a second recommendation list to each surveyor, wherein the second recommendation list includes a number of newly input case information sorted by matching degree by each surveyor.

[0028] Optionally, it also includes:

[0029] Step S6: constructing a second communication group based on IM communication technology, wherein the second communication group includes a number of surveyors;

[0030] Step S7: Based on the second communication group, several investigators share and communicate about the case.

[0031] A second aspect of the present application provides a surveyor case recommendation device, the device comprising:

[0032] An acquisition unit, used to acquire the conversation information between the surveyor and the parties involved in the historical case based on the IM communication technology and the processing related information of the historical case;

[0033] A feature processing unit, used to extract case interaction feature information and emotion feature information from the dialogue information;

[0034] A modeling unit, configured to construct a collaborative filtering model based on the case interaction feature information, the sentiment feature information, and the processing result information of the historical cases of the surveyor;

[0035] The first recommendation unit is used to analyze the newly input case information based on the collaborative filtering model to form a first recommendation list, wherein the first recommendation list contains a plurality of surveyor information that meets the preset matching.

[0036] Optionally, the acquiring unit is specifically used for:

[0037] When the surveyor handles a historical case, a first communication group for the historical case is established based on IM communication technology, wherein the first communication group includes the surveyor and parties related to the historical case;

[0038] Acquire the conversation information of the surveyor in the first communication group during the process of handling the historical case.

[0039] Optionally, the feature processing unit is specifically used to:

[0040] By analyzing the conversation information, case interaction feature information including communication frequency, average communication duration, and communication time period is extracted from the conversation information;

[0041] The natural language processing technology is used to perform sentiment analysis on the dialogue information, and the sentiment feature information of the dialogue information is extracted based on the keywords contained in the dialogue information.

[0042] Optionally, the modeling unit is specifically used for:

[0043] The basic information of the surveyor and the case interaction feature information, the sentiment feature information and the processing related information of the historical cases are converted into a matrix form, and a collaborative filtering model including a surveyor-case matrix is ​​constructed;

[0044] The collaborative filtering model is trained by a collaborative filtering algorithm.

[0045] Optionally, the first recommendation unit is specifically configured to:

[0046] Extract feature information of newly input case information;

[0047] According to the characteristic information of the newly input case information, combined with the collaborative filtering model, a first recommendation list is formed, wherein the first recommendation list contains a plurality of surveyor information that meets the preset matching.

[0048] Optionally, it also includes:

[0049] The second recommendation unit is used to push a second recommendation list to each surveyor, wherein the second recommendation includes a plurality of newly input case information sorted by matching degree by each surveyor.

[0050] Optionally, a communication unit is further included, for:

[0051] Building a second communication group based on IM communication technology, wherein the second communication group includes a number of surveyors;

[0052] Based on the second communication group, several investigators share and communicate about cases.

[0053] A third aspect of the present application provides a surveyor case recommendation device, the device comprising a processor and a memory:

[0054] The memory is used to store program code and transmit the program code to the processor;

[0055] The processor is used to execute the steps of the method for recommending cases to surveyors as described in the first aspect above according to the instructions in the program code.

[0056] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store program code, and the program code is used to execute the method described in the first aspect above.

[0057] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0058] In the present application, a method, device, equipment and storage medium for recommending cases for investigators are provided. By extracting the features of historical cases, including the interactive information between the investigator and the relevant parties of the historical cases during the case handling process, a collaborative filtering model is constructed, and new cases are recommended based on the collaborative filtering model, so that the recommendation results are more accurate. At the same time, based on IM communication technology, real-time communication and collaborative work on cases can be facilitated, thereby improving the work efficiency and service quality of investigators, and solving the technical problems that traditional case investigation and recommendation methods mainly rely on manual experience and knowledge, and have low efficiency and low accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A method flow chart of the method for recommending cases to surveyors in an embodiment of the present application;

[0060] Figure 2 This is a schematic diagram of the structure of the surveyor case recommendation device in the embodiment of the present application;

[0061] Figure 3 This is a schematic diagram of the structure of the surveyor case recommendation equipment in the embodiment of the present application. DETAILED DESCRIPTION

[0062] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0063] The present application designs a method, device, equipment and storage medium for case recommendation for investigators, which solves the technical problems that traditional case investigation and recommendation methods mainly rely on manual experience and knowledge, and have low efficiency and low accuracy.

[0064] For easier understanding, see Figure 1 , Figure 1 Flow chart of the method for recommending cases to surveyors in the embodiment of the present application. Figure 1 As shown, specifically:

[0065] Step S1, obtaining the conversation information between the investigator and the parties involved in the historical case based on the IM communication technology and the relevant information on the handling of the historical case;

[0066] It should be noted that obtaining the conversation records between the investigator and the parties involved in the case through IM communication technology may require interfacing with the IM system or extracting relevant data from the database.

[0067] In addition, you can also clean the conversation records and remove irrelevant information, such as advertisements, repeated information, etc.

[0068] Associate conversation information with case processing information to ensure that each conversation can correspond to a specific case and investigator.

[0069] The specific process can be:

[0070] Interface connection: Develop API or use existing API to obtain data from IM system.

[0071] Data cleaning tools: Use regular expressions, text processing libraries (such as NLTK, spaCy), and other tools to clean data.

[0072] Data association: Associate conversation records with case processing information through case ID or investigator ID.

[0073] Step S2, extracting case interaction feature information and sentiment feature information from the dialogue information;

[0074] It should be noted that interactive feature extraction: analyze the conversation content and extract keywords and phrases related to case handling, such as case type, processing time, etc.

[0075] Emotional feature extraction: Use sentiment analysis tools (such as VADER, TextBlob) to analyze the emotional tendencies in conversations.

[0076] Step S3: constructing a collaborative filtering model based on case interaction feature information, sentiment feature information, and historical case processing result information of the investigator;

[0077] It should be noted that the surveyor and case information are constructed into a user-item matrix, in which each element represents the surveyor's handling of the case, and a collaborative filtering algorithm (such as matrix decomposition and K-nearest neighbor) is used to train the model.

[0078] Step S4: Based on the collaborative filtering model, the newly input case information is analyzed to form a first recommendation list, which includes information of several surveyors that meet the preset matching.

[0079] It should be noted that feature extraction is performed on the newly input case information, which is similar to step S2.

[0080] Use the trained collaborative filtering model to predict the matching degree between new cases and investigators and generate a recommendation list.

[0081] Furthermore, step S1 specifically includes:

[0082] When the surveyor handles a historical case, a first communication group for the historical case is established based on IM communication technology, and the first communication group includes the surveyor and parties related to the historical case;

[0083] The conversation information of the investigator in the first communication group during the process of handling the historical case is obtained.

[0084] It should be noted that the function of the IM communication technology platform is used to create a group and add the surveyor and related parties to the group.

[0085] Identify members: Identify all members who need to join the group based on the case records.

[0086] Create a group: Create a group on the IM platform and set appropriate permissions and privacy settings.

[0087] Invite members: Use the invitation function of the IM platform to add all relevant members to the group.

[0088] The specific method for obtaining the conversation information is as follows:

[0089] Data interface: Use the API or other data export functions provided by the IM platform to obtain conversation information within the group.

[0090] Data storage: Store the acquired conversation information in a format and database suitable for analysis.

[0091] Process refinement:

[0092] API calls: Write scripts or use existing tools to get conversation data through the API.

[0093] Data format: Make sure conversation data is stored in a structured format, such as JSON or CSV.

[0094] Data security: Ensuring compliance with data protection regulations during data transmission and storage.

[0095] Furthermore, step S2 specifically includes:

[0096] By analyzing the conversation information, case interaction feature information including communication frequency, average communication duration, and communication time period is extracted;

[0097] Natural language processing technology is used to perform sentiment analysis on dialogue information, and the sentiment feature information of the dialogue information is extracted based on the keywords contained in the dialogue information.

[0098] It should be noted that all relevant conversation information is collected from the IM communication group and pre-processed, including removing irrelevant characters, formatting date and time, etc.

[0099] Analyze conversation information to identify communication frequency, average duration, and time periods. Among them:

[0100] Communication frequency: count the number of conversations for each case;

[0101] Average duration: Calculate the duration of each conversation and find the average;

[0102] Time period: Identifies the time period when the conversation occurred, such as morning, afternoon, or evening.

[0103] Select appropriate sentiment analysis tools or libraries, such as VADER, TextBlob, etc., to analyze the sentiment tendency of the conversation information. Specifically, you can extract keywords from the conversation information to identify sentiment features.

[0104] Furthermore, step S3 specifically includes:

[0105] The basic information of the investigators and the case interaction feature information, sentiment feature information and processing-related information of historical cases are converted into a matrix form, and a collaborative filtering model including the investigator-case matrix is ​​constructed;

[0106] The collaborative filtering model is trained through the collaborative filtering algorithm.

[0107] It should be noted that the user-item matrix is ​​constructed: the surveyor and case information are constructed into a user-item matrix, in which each element represents the surveyor's handling of the case.

[0108] Model training: Use collaborative filtering algorithms (such as matrix decomposition, K-nearest neighbor) to train the model. Specifically: Matrix construction: Convert the surveyor and case information into a matrix form, where the rows of the matrix represent the surveyors and the columns represent the cases.

[0109] Algorithm selection: Select a suitable collaborative filtering algorithm based on data characteristics.

[0110] Model training: Use historical data to train the model and adjust parameters to optimize model performance.

[0111] Furthermore, step S4 specifically includes:

[0112] Extract feature information of newly input case information;

[0113] According to the characteristic information of the newly input case information, combined with the collaborative filtering model, a first recommendation list is formed, and the first recommendation list contains information of several surveyors that meet the preset matching.

[0114] It should be noted that feature extraction: feature extraction is performed on the dialogue information of new cases to extract interaction features and emotional features.

[0115] Matching degree calculation: Use the model to predict the matching degree between new cases and each investigator.

[0116] Recommendation list generation: Generate a recommendation list based on the matching degree, listing the most matching surveyor information.

[0117] Furthermore, after step S4, the following steps are further included:

[0118] Step S5: Push a second recommendation list to each surveyor, where the second recommendation list includes a number of newly input case information sorted by matching degree by each surveyor.

[0119] It should be noted that the collaborative filtering model constructed previously is used to generate a personalized case recommendation list for each surveyor.

[0120] The recommendation list is pushed to the surveyor through IM communication technology or other notification channels.

[0121] Process refinement:

[0122] Generate recommendations: Based on the model analysis results, generate a recommendation list containing new case information for each investigator.

[0123] Matching degree sorting: Sort the cases in the recommendation list by matching degree.

[0124] Push notification: The recommendation list will be sent to the surveyor through the push function of the IM platform or email, SMS, etc.

[0125] Furthermore, it also includes:

[0126] Step S6: constructing a second communication group based on IM communication technology, wherein the second communication group includes a number of surveyors;

[0127] Step S7: Based on the second communication group, several investigators share and communicate about the case.

[0128] It should be noted that the surveyors who participated in the case discussion were selected based on the recommendation list and the surveyors' feedback. A second communication group was created using IM communication technology.

[0129] Select surveyors: Based on the recommendation list and case requirements, determine the list of surveyors to participate in the discussion.

[0130] Create a group: Create a second communication group on the IM platform and add the selected surveyors to the group.

[0131] Set permissions: Set group permissions and rules based on the needs of case discussion.

[0132] In the second communication group, investigators can share case information, discuss case details, and make recommendations.

[0133] Case sharing: Investigators can share case details and related materials in the group.

[0134] Open Discussion: Investigators are encouraged to have open discussions about cases in the group and share their views and experiences.

[0135] Information Recording: Ensure that all discussions in the group are recorded and archived for subsequent analysis and reference.

[0136] Furthermore, you can:

[0137] Collect surveyors' feedback on the recommendation system to understand its effectiveness and user satisfaction.

[0138] The recommendation model is continuously iterated and optimized based on surveyor feedback and new case data.

[0139] Establish a knowledge base to integrate effective information and solutions from group discussions for reference by all surveyors.

[0140] See also Figure 2 , Figure 2 Schematic diagram of the structure of the surveyor case recommendation device in the embodiment of the present application. Figure 2 As shown, specifically:

[0141] The acquisition unit 201 is used to acquire the conversation information between the investigator and the parties involved in the historical case based on the IM communication technology and the information related to the handling of the historical case;

[0142] It should be noted that obtaining the conversation records between the investigator and the parties involved in the case through IM communication technology may require interfacing with the IM system or extracting relevant data from the database.

[0143] In addition, you can also clean the conversation records and remove irrelevant information, such as advertisements, repeated information, etc.

[0144] Associate conversation information with case processing information to ensure that each conversation can correspond to a specific case and investigator.

[0145] The specific process can be:

[0146] Interface connection: Develop API or use existing API to obtain data from IM system.

[0147] Data cleaning tools: Use regular expressions, text processing libraries (such as NLTK, spaCy), and other tools to clean data.

[0148] Data association: Associate conversation records with case processing information through case ID or investigator ID.

[0149] A feature processing unit 202, used to extract case interaction feature information and emotion feature information from the dialogue information;

[0150] It should be noted that interactive feature extraction: analyze the conversation content and extract keywords and phrases related to case handling, such as case type, processing time, etc.

[0151] Emotional feature extraction: Use sentiment analysis tools (such as VADER, TextBlob) to analyze the emotional tendencies in conversations.

[0152] A modeling unit 203, used to build a collaborative filtering model based on case interaction feature information, sentiment feature information, and historical case processing result information of the investigator;

[0153] It should be noted that the surveyor and case information are constructed into a user-item matrix, in which each element represents the surveyor's handling of the case, and a collaborative filtering algorithm (such as matrix decomposition and K-nearest neighbor) is used to train the model.

[0154] The first recommendation unit 204 is used to analyze the newly input case information based on the collaborative filtering model to form a first recommendation list, which includes information of several surveyors that meet the preset matching.

[0155] It should be noted that feature extraction is performed on the newly input case information, which is similar to step S2.

[0156] Use the trained collaborative filtering model to predict the matching degree between new cases and investigators and generate a recommendation list.

[0157] Furthermore, the acquisition unit 201 is specifically used for:

[0158] When the surveyor handles a historical case, a first communication group for the historical case is established based on IM communication technology, and the first communication group includes the surveyor and parties related to the historical case;

[0159] The conversation information of the investigator in the first communication group during the process of handling the historical case is obtained.

[0160] It should be noted that the function of the IM communication technology platform is used to create a group and add the surveyor and related parties to the group.

[0161] Identify members: Identify all members who need to join the group based on the case records.

[0162] Create a group: Create a group on the IM platform and set appropriate permissions and privacy settings.

[0163] Invite members: Use the invitation function of the IM platform to add all relevant members to the group.

[0164] The specific method for obtaining the conversation information is as follows:

[0165] Data interface: Use the API or other data export functions provided by the IM platform to obtain conversation information within the group.

[0166] Data storage: Store the acquired conversation information in a format and database suitable for analysis.

[0167] Process refinement:

[0168] API calls: Write scripts or use existing tools to get conversation data through the API.

[0169] Data format: Make sure conversation data is stored in a structured format, such as JSON or CSV.

[0170] Data security: Ensuring compliance with data protection regulations during data transmission and storage.

[0171] Furthermore, the feature processing unit 202 is specifically used for:

[0172] By analyzing the conversation information, case interaction feature information including communication frequency, average communication duration, and communication time period is extracted;

[0173] Natural language processing technology is used to perform sentiment analysis on dialogue information, and the sentiment feature information of the dialogue information is extracted based on the keywords contained in the dialogue information.

[0174] It should be noted that all relevant conversation information is collected from the IM communication group and pre-processed, including removing irrelevant characters, formatting date and time, etc.

[0175] Analyze conversation information to identify communication frequency, average duration, and time periods. Among them:

[0176] Communication frequency: count the number of conversations for each case;

[0177] Average duration: Calculate the duration of each conversation and find the average;

[0178] Time period: Identifies the time period when the conversation occurred, such as morning, afternoon, or evening.

[0179] Select appropriate sentiment analysis tools or libraries, such as VADER, TextBlob, etc., to analyze the sentiment tendency of the conversation information. Specifically, you can extract keywords from the conversation information to identify sentiment features.

[0180] Furthermore, the modeling unit 203 is specifically used for:

[0181] The basic information of the investigators and the case interaction feature information, sentiment feature information and processing-related information of historical cases are converted into a matrix form, and a collaborative filtering model including the investigator-case matrix is ​​constructed;

[0182] The collaborative filtering model is trained through the collaborative filtering algorithm.

[0183] It should be noted that the user-item matrix is ​​constructed: the surveyor and case information are constructed into a user-item matrix, in which each element represents the surveyor's handling of the case.

[0184] Model training: Use collaborative filtering algorithms (such as matrix decomposition, K-nearest neighbor) to train the model. Specifically: Matrix construction: Convert the surveyor and case information into a matrix form, where the rows of the matrix represent the surveyors and the columns represent the cases.

[0185] Algorithm selection: Select a suitable collaborative filtering algorithm based on data characteristics.

[0186] Model training: Use historical data to train the model and adjust parameters to optimize model performance.

[0187] Furthermore, the first recommendation unit 204 is specifically configured to:

[0188] Extract feature information of newly input case information;

[0189] According to the characteristic information of the newly input case information, combined with the collaborative filtering model, a first recommendation list is formed, and the first recommendation list contains information of several surveyors that meet the preset matching.

[0190] It should be noted that feature extraction: feature extraction is performed on the dialogue information of new cases to extract interaction features and emotional features.

[0191] Matching degree calculation: Use the model to predict the matching degree between new cases and each investigator.

[0192] Recommendation list generation: Generate a recommendation list based on the matching degree, listing the most matching surveyor information.

[0193] Furthermore, it also includes:

[0194] The second recommendation unit is used to push a second recommendation list to each surveyor, where the second recommendation includes a number of newly input case information sorted by matching degree by each surveyor.

[0195] It should be noted that feature extraction: feature extraction is performed on the dialogue information of new cases to extract interaction features and emotional features.

[0196] Matching degree calculation: Use the model to predict the matching degree between new cases and each investigator.

[0197] Recommendation list generation: Generate a recommendation list based on the matching degree, listing the most matching surveyor information.

[0198] Furthermore, a communication unit is included, which is used to:

[0199] A second communication group is established based on IM communication technology, and the second communication group includes a number of surveyors;

[0200] Based on the second communication group, several investigators share and communicate about cases.

[0201] It should be noted that the surveyors who participated in the case discussion were selected based on the recommendation list and the surveyors' feedback. A second communication group was created using IM communication technology.

[0202] Select surveyors: Based on the recommendation list and case requirements, determine the list of surveyors to participate in the discussion.

[0203] Create a group: Create a second communication group on the IM platform and add the selected surveyors to the group.

[0204] Set permissions: Set group permissions and rules based on the needs of case discussion.

[0205] In the second communication group, investigators can share case information, discuss case details, and make recommendations.

[0206] Case sharing: Investigators can share case details and related materials in the group.

[0207] Open Discussion: Investigators are encouraged to have open discussions about cases in the group and share their views and experiences.

[0208] Information Recording: Ensure that all discussions in the group are recorded and archived for subsequent analysis and reference.

[0209] Furthermore, you can:

[0210] Collect surveyors' feedback on the recommendation system to understand its effectiveness and user satisfaction.

[0211] The recommendation model is continuously iterated and optimized based on surveyor feedback and new case data.

[0212] Establish a knowledge base to integrate effective information and solutions from group discussions for reference by all surveyors.

[0213] The present application embodiment also provides another surveyor case recommendation device, such as Figure 3For the sake of convenience, only the parts related to the embodiments of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiments of the present application. The terminal can be any terminal device including a mobile phone, a tablet computer, a personal digital assistant (English full name: Personal Digital Assistant, English abbreviation: PDA), a sales terminal (English full name: Point of Sales, English abbreviation: POS), a car computer, etc., taking the terminal as a mobile phone as an example:

[0214] Figure 3 FIG. 1 is a block diagram showing a partial structure of a mobile phone related to a terminal provided in an embodiment of the present application. Figure 3 The mobile phone includes: a radio frequency (RF) circuit 1010, a memory 1020, an input unit 1030, a display unit 1040, a sensor 1050, an audio circuit 1060, a wireless fidelity (WiFi) module 1070, a processor 1080, and a power supply 1090. Those skilled in the art can understand that Figure 3 The mobile phone structure shown in the figure does not constitute a limitation on the mobile phone, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0215] Combine the following Figure 3 A detailed introduction to the various components of the mobile phone:

[0216] The RF circuit 1010 can be used for receiving and sending signals during information transmission or calls. In particular, after receiving the downlink information of the base station, it is sent to the processor 1080 for processing; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit 1010 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (full name: Low Noise Amplifier, English abbreviation: LNA), a duplexer, etc. In addition, the RF circuit 1010 can also communicate with the network and other devices through wireless communication. The above-mentioned wireless communications can use any communication standard or protocol, including but not limited to Global System of Mobile communications (Global System of Mobile communication, English abbreviation: GSM), General Packet Radio Service (General Packet Radio Service, GPRS), Code Division Multiple Access (Code Division Multiple Access, English abbreviation: CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (Long Term Evolution, English abbreviation: LTE), e-mail, Short Messaging Service (SMS), etc.

[0217] The memory 1020 can be used to store software programs and modules. The processor 1080 executes various functional applications and data processing of the mobile phone by running the software programs and modules stored in the memory 1020. The memory 1020 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 1020 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0218] The input unit 1030 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the mobile phone. Specifically, the input unit 1030 may include a touch panel 1031 and other input devices 1032. The touch panel 1031, also known as a touch screen, can collect the user's touch operation on or near it (such as the user's operation on the touch panel 1031 or near the touch panel 1031 using any suitable object or accessory such as a finger, stylus, etc.), and drive the corresponding connection device according to a pre-set program. Optionally, the touch panel 1031 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 1080, and can receive and execute the command sent by the processor 1080. In addition, the touch panel 1031 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch panel 1031, the input unit 1030 may further include other input devices 1032. Specifically, the other input devices 1032 may include but are not limited to one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

[0219] The display unit 1040 can be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 1040 may include a display panel 1041. Optionally, the display panel 1041 may be configured in the form of a liquid crystal display (full name in English: Liquid Crystal Display, English abbreviation: LCD), an organic light-emitting diode (full name in English: Organic Light-Emitting Diode, English abbreviation: OLED), etc. Further, the touch panel 1031 may cover the display panel 1041. When the touch panel 1031 detects a touch operation on or near it, it is transmitted to the processor 1080 to determine the type of touch event. Subsequently, the processor 1080 provides a corresponding visual output on the display panel 1041 according to the type of touch event. Although in Figure 3 In the embodiment, the touch panel 1031 and the display panel 1041 are used as two independent components to realize the input and output functions of the mobile phone, but in some embodiments, the touch panel 1031 and the display panel 1041 can be integrated to realize the input and output functions of the mobile phone.

[0220] The mobile phone may also include at least one sensor 1050, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 1041 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 1041 and / or the backlight when the mobile phone is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that can be configured in the mobile phone, such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be repeated here.

[0221] The audio circuit 1060, the speaker 1061, and the microphone 1062 can provide an audio interface between the user and the mobile phone. The audio circuit 1060 can transmit the received audio data to the speaker 1061 after converting the received audio data into an electrical signal, which is converted into a sound signal for output; on the other hand, the microphone 1062 converts the collected sound signal into an electrical signal, which is received by the audio circuit 1060 and converted into audio data, and then the audio data is output to the processor 1080 for processing, and then sent to another mobile phone through the RF circuit 1010, or the audio data is output to the memory 1020 for further processing.

[0222] WiFi is a short-range wireless transmission technology. The mobile phone can help users send and receive emails, browse web pages and access streaming media through the WiFi module 1070. It provides users with wireless broadband Internet access. Figure 3 A WiFi module 1070 is shown, but it is understandable that it is not an essential component of the mobile phone and can be omitted as needed without changing the essence of the invention.

[0223] The processor 1080 is the control center of the mobile phone. It uses various interfaces and lines to connect various parts of the entire mobile phone. By running or executing software programs and / or modules stored in the memory 1020 and calling data stored in the memory 1020, it executes various functions of the mobile phone and processes data, thereby monitoring the mobile phone as a whole. Optionally, the processor 1080 may include one or more processing units; preferably, the processor 1080 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 1080.

[0224] The mobile phone also includes a power supply 1090 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 1080 through a power management system, so that the power management system can manage functions such as charging, discharging, and power consumption.

[0225] Although not shown, the mobile phone may also include a camera, a Bluetooth module, etc., which will not be described in detail here.

[0226] In the embodiment of the present application, the processor 1080 included in the terminal also has the following functions:

[0227] Step S1, obtaining the conversation information between the investigator and the parties involved in the historical case based on the IM communication technology and the relevant information on the handling of the historical case;

[0228] It should be noted that obtaining the conversation records between the investigator and the parties involved in the case through IM communication technology may require interfacing with the IM system or extracting relevant data from the database.

[0229] In addition, you can also clean the conversation records and remove irrelevant information, such as advertisements, repeated information, etc.

[0230] Associate conversation information with case processing information to ensure that each conversation can correspond to a specific case and investigator.

[0231] The specific process can be:

[0232] Interface connection: Develop API or use existing API to obtain data from IM system.

[0233] Data cleaning tools: Use regular expressions, text processing libraries (such as NLTK, spaCy), and other tools to clean data.

[0234] Data association: Associate conversation records with case processing information through case ID or investigator ID.

[0235] Step S2, extracting case interaction feature information and sentiment feature information from the dialogue information;

[0236] It should be noted that interactive feature extraction: analyze the conversation content and extract keywords and phrases related to case handling, such as case type, processing time, etc.

[0237] Emotional feature extraction: Use sentiment analysis tools (such as VADER, TextBlob) to analyze the emotional tendencies in conversations.

[0238] Step S3: constructing a collaborative filtering model based on case interaction feature information, sentiment feature information, and historical case processing result information of the investigator;

[0239] It should be noted that the surveyor and case information are constructed into a user-item matrix, in which each element represents the surveyor's handling of the case, and a collaborative filtering algorithm (such as matrix decomposition and K-nearest neighbor) is used to train the model.

[0240] Step S4: Based on the collaborative filtering model, the newly input case information is analyzed to form a first recommendation list, which includes information of several surveyors that meet the preset matching.

[0241] It should be noted that feature extraction is performed on the newly input case information, which is similar to step S2.

[0242] Use the trained collaborative filtering model to predict the matching degree between new cases and investigators and generate a recommendation list.

[0243] Furthermore, step S1 specifically includes:

[0244] When the surveyor handles a historical case, a first communication group for the historical case is established based on IM communication technology, and the first communication group includes the surveyor and parties related to the historical case;

[0245] The conversation information of the investigator in the first communication group during the process of handling the historical case is obtained.

[0246] It should be noted that the function of the IM communication technology platform is used to create a group and add the surveyor and related parties to the group.

[0247] Identify members: Identify all members who need to join the group based on the case records.

[0248] Create a group: Create a group on the IM platform and set appropriate permissions and privacy settings.

[0249] Invite members: Use the invitation function of the IM platform to add all relevant members to the group.

[0250] The specific method for obtaining the conversation information is as follows:

[0251] Data interface: Use the API or other data export functions provided by the IM platform to obtain conversation information within the group.

[0252] Data storage: Store the acquired conversation information in a format and database suitable for analysis.

[0253] Process refinement:

[0254] API calls: Write scripts or use existing tools to get conversation data through the API.

[0255] Data format: Make sure conversation data is stored in a structured format, such as JSON or CSV.

[0256] Data security: Ensuring compliance with data protection regulations during data transmission and storage.

[0257] Furthermore, step S2 specifically includes:

[0258] By analyzing the conversation information, case interaction feature information including communication frequency, average communication duration, and communication time period is extracted;

[0259] Natural language processing technology is used to perform sentiment analysis on dialogue information, and the sentiment feature information of the dialogue information is extracted based on the keywords contained in the dialogue information.

[0260] It should be noted that all relevant conversation information is collected from the IM communication group and pre-processed, including removing irrelevant characters, formatting date and time, etc.

[0261] Analyze conversation information to identify communication frequency, average duration, and time periods. Among them:

[0262] Communication frequency: count the number of conversations for each case;

[0263] Average duration: Calculate the duration of each conversation and find the average;

[0264] Time period: Identifies the time period when the conversation occurred, such as morning, afternoon, or evening.

[0265] Select appropriate sentiment analysis tools or libraries, such as VADER, TextBlob, etc., to analyze the sentiment tendency of the conversation information. Specifically, you can extract keywords from the conversation information to identify sentiment features.

[0266] Furthermore, step S3 specifically includes:

[0267] The basic information of the investigators and the case interaction feature information, sentiment feature information and processing-related information of historical cases are converted into a matrix form, and a collaborative filtering model including the investigator-case matrix is ​​constructed;

[0268] The collaborative filtering model is trained through the collaborative filtering algorithm.

[0269] It should be noted that the user-item matrix is ​​constructed: the surveyor and case information are constructed into a user-item matrix, in which each element represents the surveyor's handling of the case.

[0270] Model training: Use collaborative filtering algorithms (such as matrix decomposition, K-nearest neighbor) to train the model. Specifically: Matrix construction: Convert the surveyor and case information into a matrix form, where the rows of the matrix represent the surveyors and the columns represent the cases.

[0271] Algorithm selection: Select a suitable collaborative filtering algorithm based on data characteristics.

[0272] Model training: Use historical data to train the model and adjust parameters to optimize model performance.

[0273] Furthermore, step S4 specifically includes:

[0274] Extract feature information of newly input case information;

[0275] According to the characteristic information of the newly input case information, combined with the collaborative filtering model, a first recommendation list is formed, and the first recommendation list contains information of several surveyors that meet the preset matching.

[0276] It should be noted that feature extraction: feature extraction is performed on the dialogue information of new cases to extract interaction features and emotional features.

[0277] Matching degree calculation: Use the model to predict the matching degree between new cases and each investigator.

[0278] Recommendation list generation: Generate a recommendation list based on the matching degree, listing the most matching surveyor information.

[0279] Furthermore, after step S4, the following steps are further included:

[0280] Step S5: Push a second recommendation list to each surveyor, where the second recommendation list includes a number of newly input case information sorted by matching degree by each surveyor.

[0281] It should be noted that the collaborative filtering model constructed previously is used to generate a personalized case recommendation list for each surveyor.

[0282] The recommendation list is pushed to the surveyor through IM communication technology or other notification channels.

[0283] Process refinement:

[0284] Generate recommendations: Based on the model analysis results, generate a recommendation list containing new case information for each investigator.

[0285] Matching degree sorting: Sort the cases in the recommendation list by matching degree.

[0286] Push notification: The recommendation list will be sent to the surveyor through the push function of the IM platform or email, SMS, etc.

[0287] Furthermore, it also includes:

[0288] Step S6: constructing a second communication group based on IM communication technology, wherein the second communication group includes a number of surveyors;

[0289] Step S7: Based on the second communication group, several investigators share and communicate about the case.

[0290] It should be noted that the surveyors who participated in the case discussion were selected based on the recommendation list and the surveyors' feedback. A second communication group was created using IM communication technology.

[0291] Select surveyors: Based on the recommendation list and case requirements, determine the list of surveyors to participate in the discussion.

[0292] Create a group: Create a second communication group on the IM platform and add the selected surveyors to the group.

[0293] Set permissions: Set group permissions and rules based on the needs of case discussion.

[0294] In the second communication group, investigators can share case information, discuss case details, and make recommendations.

[0295] Case sharing: Investigators can share case details and related materials in the group.

[0296] Open Discussion: Investigators are encouraged to have open discussions about cases in the group and share their views and experiences.

[0297] Information Recording: Ensure that all discussions in the group are recorded and archived for subsequent analysis and reference.

[0298] Furthermore, you can:

[0299] Collect surveyors' feedback on the recommendation system to understand its effectiveness and user satisfaction.

[0300] The recommendation model is continuously iterated and optimized based on surveyor feedback and new case data.

[0301] Establish a knowledge base to integrate effective information and solutions from group discussions for reference by all surveyors.

[0302] The embodiment of the present application also provides a computer-readable storage medium for storing program code, wherein the program code is used to execute any one of the implementation methods of the surveyor case recommendation method described in the aforementioned embodiments.

[0303] In the embodiments of the present application, a method, device, equipment and storage medium for recommending cases to investigators are provided. By extracting features of historical cases, including the interactive information between the investigator and the relevant parties of the historical cases during the case handling process, a collaborative filtering model is constructed, and new cases are recommended based on the collaborative filtering model, so that the recommendation results are more accurate. At the same time, based on IM communication technology, real-time communication and collaborative work on cases can be facilitated, thereby improving the work efficiency and service quality of investigators, and solving the technical problems of low efficiency and low accuracy of traditional case investigation and recommendation methods that mainly rely on manual experience and knowledge.

[0304] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0305] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0306] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0307] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0308] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0309] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0310] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.

[0311] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for recommending cases to surveyors, characterized in that: include: Step S1, obtaining the conversation information between the surveyor and the parties involved in the historical case based on the IM communication technology and the relevant information on the handling of the historical case; Step S2, extracting case interaction feature information and emotion feature information from the dialogue information; Step S3, constructing a collaborative filtering model based on the case interaction feature information, the sentiment feature information, and the processing result information of the historical cases of the surveyor; Step S4: Based on the collaborative filtering model, the newly input case information is analyzed to form a first recommendation list, wherein the first recommendation list contains information of several surveyors that meet the preset matching.

2. The method for recommending cases to surveyors according to claim 1, characterized in that: The step S1 specifically includes: When the surveyor handles a historical case, a first communication group for the historical case is established based on IM communication technology, wherein the first communication group includes the surveyor and parties related to the historical case; Acquire the conversation information of the surveyor in the first communication group during the process of handling the historical case.

3. The method for recommending cases to surveyors according to claim 1, characterized in that: The step S2 specifically includes: By analyzing the conversation information, case interaction feature information including communication frequency, average communication duration, and communication time period is extracted from the conversation information; The natural language processing technology is used to perform sentiment analysis on the dialogue information, and the sentiment feature information of the dialogue information is extracted based on the keywords contained in the dialogue information.

4. The method for recommending cases to surveyors according to claim 1, characterized in that: The step S3 specifically includes: The basic information of the surveyor and the case interaction feature information, the sentiment feature information and the processing related information of the historical cases are converted into a matrix form, and a collaborative filtering model including a surveyor-case matrix is ​​constructed; The collaborative filtering model is trained by a collaborative filtering algorithm.

5. The method for recommending cases to surveyors according to claim 1, characterized in that: The step S4 specifically includes: Extract feature information of newly input case information; According to the characteristic information of the newly input case information, combined with the collaborative filtering model, a first recommendation list is formed, wherein the first recommendation list contains a plurality of surveyor information that meets the preset matching.

6. The method for recommending cases to surveyors according to claim 1, characterized in that: After step S4, the following steps are also included: Step S5: Push a second recommendation list to each surveyor, wherein the second recommendation list includes a number of newly input case information sorted by matching degree by each surveyor.

7. The method for recommending cases to surveyors according to claim 1, characterized in that: Also includes: Step S6: constructing a second communication group based on IM communication technology, wherein the second communication group includes a number of surveyors; Step S7: Based on the second communication group, several investigators share and communicate about the case.

8. A case recommendation device for surveyors, characterized in that: include: An acquisition unit, used to acquire the conversation information between the surveyor and the parties involved in the historical case based on the IM communication technology and the processing related information of the historical case; A feature processing unit, used to extract case interaction feature information and emotion feature information from the dialogue information; A modeling unit, configured to construct a collaborative filtering model based on the case interaction feature information, the sentiment feature information, and the processing result information of the historical cases of the surveyor; The first recommendation unit is used to analyze the newly input case information based on the collaborative filtering model to form a first recommendation list, wherein the first recommendation list contains a plurality of surveyor information that meets the preset matching.

9. A surveyor case recommendation device, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the surveyor case recommendation method described in any one of claims 1-7 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code, and the program code is used to execute the surveyor case recommendation method described in any one of claims 1-7.

Images