Repair institution position information recommendation method and device, equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, and provides a position information recommendation method and device of a repair institution, equipment and a storage medium, the method is applied to a server, and comprises the steps that input information sent by terminal equipment is acquired, and the input information indicates that a user needs the repair institution; acquiring following case attribute information of the user; segmenting a text corresponding to the input information and the associated case attribute information to obtain a word list; words in the word list are matched with mechanism names in a preset repair mechanism list, a matching result is obtained, and the repair mechanism list comprises at least one repair mechanism; determining a target repair mechanism according to a matching result; and sending the target position information of the target repairing mechanism to the terminal equipment. According to the method, the requirements of the user are fully considered, and personalized recommendation is realized; the target repair mechanism is determined according to the matching result, and the most appropriate repair mechanism can be recommended to the user, so that the accuracy of recommending the repair mechanism is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and storage medium for recommending location information of a repair organization. Background Art

[0002] Car insurance claims are a very important claim service for insurance companies. When a user's car needs to be repaired, it is particularly important to recommend a suitable repair organization to the user. Related technologies generally use automatic speech recognition (ASR) technology to convert the information of the repair organization in the voice into text in real time, and then the staff enters the text into the claims system to recommend a suitable repair organization to the user. This method cannot achieve personalized recommendations, resulting in the recommended repair organization failing to meet the needs of users. Summary of the invention

[0003] The main purpose of this application is to provide a method, device, equipment and storage medium for recommending the location information of a repair organization, which fully considers the needs of users, realizes personalized recommendations, determines the target repair organization based on the matching results, and can recommend the most suitable repair organization to users, thereby improving the accuracy of recommending repair organizations.

[0004] In a first aspect, the present application provides a method for recommending location information of a repair organization, which is applied to a server and includes:

[0005] Acquire input information sent by the terminal device, wherein the input information indicates that the user needs a repair mechanism;

[0006] Get the user's case attribute information;

[0007] Segmenting the text corresponding to the input information and the accompanying attribute information to obtain a word list;

[0008] Matching the words in the word list with the names of institutions in a preset repair institution list to obtain a matching result, wherein the repair institution list includes at least one repair institution;

[0009] Determining a target repair mechanism according to the matching result;

[0010] The target location information of the target repair mechanism is sent to the terminal device.

[0011] In a second aspect, the present application further provides a location information recommendation device for a repair organization, which is applied to a server and includes:

[0012] A first acquisition module, used to acquire input information sent by the terminal device, wherein the input information indicates that the user needs a repair mechanism;

[0013] The second acquisition module is used to obtain the user's case attribute information;

[0014] A segmentation module, used for segmenting the text corresponding to the input information and the accompanying attribute information to obtain a word list;

[0015] A matching module, used for matching the words in the word list with the names of institutions in a preset repair institution list to obtain a matching result, wherein the repair institution list includes at least one repair institution;

[0016] A mechanism determination module, used to determine a target repair mechanism according to the matching result;

[0017] A sending module is used to send the target location information of the target repair mechanism to the terminal device.

[0018] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor;

[0019] The memory is used to store computer programs;

[0020] The processor is used to execute the computer program and implement the above-mentioned method for recommending location information of the repair mechanism when executing the computer program.

[0021] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for recommending location information of a repair mechanism as described above are implemented.

[0022] The present application provides a method, device, equipment and storage medium for recommending location information of a repair organization, wherein the method is applied to a server, and includes: obtaining input information sent by a terminal device, wherein the input information indicates that a user needs a repair organization; obtaining the user's accompanying attribute information; segmenting the text corresponding to the input information and the accompanying attribute information to obtain a word list; matching the words in the word list with the organization names in a preset repair organization list to obtain a matching result, wherein the repair organization list includes at least one repair organization; determining a target repair organization based on the matching result; and sending the target location information of the target repair organization to the terminal device. The present application fully considers the user's needs and realizes personalized recommendation by segmenting the input information sent by the user and the user's accompanying attribute information to obtain a word list, and matching the word list with the preset repair organization list. The target repair organization is determined based on the matching result, and the most suitable repair organization can be recommended to the user, thereby improving the accuracy of the recommended repair organization. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 A schematic diagram of a flow chart of a method for recommending location information of a repair organization provided in an embodiment of the present application;

[0025] Figure 2 A schematic diagram of the connection between the server and the terminal device provided in the embodiment of the present application;

[0026] Figure 3 A schematic block diagram of a device for recommending location information of a repair organization provided in an embodiment of the present application;

[0027] Figure 4 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are 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.

[0029] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0030] The embodiment of the present application provides a method, device, equipment and storage medium for recommending location information of a repair organization. The method for recommending location information of a repair organization can be applied to a server, which can be a separate server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0031] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0032] See also Figure 1 , Figure 1 This is a flow chart of a method for recommending location information of a repair organization provided in an embodiment of the present application. It should be noted that the method for recommending location information of a repair organization provided in an embodiment of the present application can be used in a server.

[0033] like Figure 2 As shown, the repair organization location information recommendation method is applied to a server, the server and the terminal device are in communication connection, and the target location information obtained by the repair organization location information recommendation method can be sent to the terminal device through the server. Of course, it is not limited to this and is not limited here.

[0034] In specific implementation, the terminal device includes but is not limited to: any one of a mobile phone, a tablet computer, a laptop computer, and a desktop computer; the server can be a single server or a server cluster, or a cloud server that provides cloud computing services.

[0035] like Figure 1 As shown, the method for recommending location information of a repair organization is applied to a server and includes steps S101 to S106.

[0036] Step S101: obtaining input information sent by a terminal device, wherein the input information indicates that a user needs a repair mechanism.

[0037] For example, the terminal device may be a user's mobile phone, tablet, or a device in the user's vehicle, etc. The input information may include the user's description of vehicle failure and insurance needs. For example, in automobile insurance, traffic accidents, vehicle thefts, etc. are all insurance accidents. When the user's vehicle encounters the aforementioned insurance accidents, the user can report the case to the insurance company through the terminal device and send text or voice information about the vehicle collision, the location of the accident, and the need to go to a repair agency for repairs.

[0038] For example, if the user sends a voice message through the terminal device, the voice message can be converted into a text message. If the user sends the location information of a repair agency or a certain area, the location information can be parsed to obtain multiple tags in the location information, such as street name, city, province, etc.

[0039] Step S102: Obtain the user's case attribute information.

[0040] In the insurance field, the accompanying attribute information of the owner of the insured vehicle may include the basic information of the owner, vehicle information, insurance contract information, insurance store, and the address of the last repair, etc.

[0041] Step S103: segment the text corresponding to the input information and the accompanying attribute information to obtain a word list.

[0042] It should be noted that segmentation is a basic task in NLP (Natural Language Processing), which refers to dividing a long text into smaller units, such as sentences, words or phrases, to facilitate subsequent text analysis, information extraction, sentiment analysis and other tasks. Segmentation generally includes two common processing methods: sentence segmentation and word segmentation. Sentence segmentation refers to dividing a text according to the boundaries of sentences to form independent sentences. This usually involves the recognition and processing of punctuation marks, such as periods, question marks, exclamation marks, etc., because these punctuation marks are usually used to mark the end of sentences. Word segmentation refers to the process of dividing sentences or texts into independent words.

[0043] The embodiment of the present application can perform sentence segmentation or word segmentation on the text corresponding to the input information and the accompanying attribute information to fully understand the actual needs of the user.

[0044] In an exemplary implementation, step S1031 to step S1033.

[0045] Step S301: Perform a first cleaning process on the input information and the case attribute information to obtain cleaned data.

[0046] Step S302: Based on a preset word segmentation algorithm, the cleaned data is segmented to obtain segmented data.

[0047] Step S303: Perform a second cleaning process on the word segmentation data to obtain a word list.

[0048] For example, during the first cleaning process, the embodiment of the present application can perform noise cleaning on the input information, unify the data format, and filter out words with low discrimination (such as vehicle brand) in the input information and the accompanying attribute information to obtain cleaned data.

[0049] The embodiment of the present application can perform sentence segmentation processing or word segmentation processing on the cleaned data based on a preset segmentation algorithm to obtain segmentation data. Specifically, the preset segmentation algorithm can include a forward maximum matching method, a reverse maximum matching method, an n-gram grammar model, and a hidden Markov model.

[0050] After word segmentation data is obtained through word segmentation processing, the word segmentation data can be cleaned for the second time to obtain a word list to improve the quality of the words in the word list, thereby improving the accuracy of text analysis.

[0051] In an exemplary implementation, step S302 includes step S3021 and step S3022.

[0052] Step S3021: construct a dictionary tree and a directed acyclic graph based on the cleaned data.

[0053] Step S3022: Based on the dynamic programming algorithm, search the dictionary tree and the directed acyclic graph to obtain word segmentation data.

[0054] Exemplarily, embodiments of the present application can construct a dictionary tree and a directed acyclic graph based on the cleaned data. It should be noted that the dictionary tree is a tree structure for quickly retrieving keys in a string data set, each node represents a prefix of a string, and the characters on the path from the root to a node are connected to form the string corresponding to the node. A directed acyclic graph is constructed based on the dependencies in the cleaned data, wherein each node in the directed acyclic graph represents an entity (such as a word), and the edges represent the relationship or dependency between these entities. Based on the maximum probability path from the starting node to any ending node based on the dynamic programming algorithm, the maximum segmentation combination based on the complete vocabulary is found to obtain word segmentation data to improve the accuracy of information filtering, thereby accurately extracting user needs.

[0055] In an exemplary embodiment, for some incomplete vocabularies, the embodiment of the present application can use a hidden Markov model and a Viterbi algorithm for processing. Specifically, the Viterbi algorithm is used to find the most likely state sequence (hidden state sequence) under a given hidden Markov model and observation sequence. It gradually constructs a path from the initial state to each possible state by means of dynamic programming, and retains the path with the highest probability until the current state. The embodiment of the present application can effectively process incomplete vocabularies in the cleaning data through a hidden Markov model and a Viterbi algorithm.

[0056] In an exemplary implementation, step S303 includes step S3031 and step S3032.

[0057] Step S3031: Filter out words in the word segmentation data whose length is greater than a preset length to obtain a first word.

[0058] Step S3032: Filter out words in the first words whose similarity is less than the second preset similarity, and obtain a word list.

[0059] For example, after the cleaning data is segmented to obtain the segmented data, the embodiment of the present application also needs to perform a second cleaning process on the segmented data. Specifically, the first word in the segmented data whose length is greater than the preset length can be screened out. For example, the preset length is 1, and the words with a length of 1 are removed, and the words with a length of 2 or more are screened out, and the length of the first words obtained is greater than the words with a preset length of 1. Furthermore, the words in the first words whose similarity is less than the second preset similarity can also be screened out. Specifically, the similarity between the words in the first words is less than the second preset similarity, indicating that the distinction between each word is high, and greater than the second preset similarity, indicating that the distinction between each word is not high. For example, auto repair, company, maintenance, repair organization, brand vehicle, etc. The embodiment of the present application can filter out redundant words by screening out words with a length greater than the preset length, and screening out words with a similarity less than the second preset similarity, thereby reducing the amount of data processed and improving the efficiency of text processing.

[0060] Step S104: Match the words in the word list with the names of institutions in a preset repair institution list to obtain a matching result, and the repair institution list includes at least one repair institution.

[0061] The word list is obtained based on the user's input information and the case attribute information. For example, the word list may include car accident, accident, license plate number, and repair. In addition, the word list may also include the name of the repair organization that the user wants to go to.

[0062] The preset repair organization list may include multiple repair organizations that cooperate with the insurance company. Generally, the repair organization repairs the insurance accident vehicle within the pricing range of the insurance company, and the insurance company pays the repair fee to the repair organization, so the policyholder does not need to pay.

[0063] For example, the embodiment of the present application matches the words in the word list with the names of the institutions in the preset repair institution list. Specifically, the names of the repair institutions appearing in the word list can be matched with the names of the institutions in the preset repair institution list. Of course, the address information appearing in the word list can also be matched with the names of the institutions in the preset repair institutions.

[0064] In an exemplary implementation, the input information includes positioning information; step S104 includes steps S1041 to S1044.

[0065] Step S401: Acquire a first repair mechanism list at a first preset distance from positioning information.

[0066] Step S402: Based on the KNN algorithm, calculate the first similarity between the words in the word list and the institution names in the first repair institution list.

[0067] Step S403: when the first similarity is less than or equal to the first preset similarity, obtain a second repair mechanism list at a second preset distance from the positioning information.

[0068] Step S404: Based on the KNN algorithm, calculate the second similarity between the words in the word list and the organization names in the second repair organization list, and determine the matching result according to the second similarity.

[0069] Exemplarily, the input information in the embodiments of the present application may include positioning information, and the positioning information may be the positioning information of a repair organization that the user wants to go to, or the positioning information of an area that the user wants to go to.

[0070] It should be noted that the KNN (K-Nearest Neighbors) algorithm is a basic and widely used classification and regression method. The KNN algorithm finds the K instances (neighbors) closest to the new input instance in the training data set and predicts the category of the new instance based on the categories of these neighbors. It is a distance-based classification method that does not require the construction of an explicit model, but directly relies on training data for prediction.

[0071] For example, the embodiment of the present application may be based on the positioning information sent by the user, and based on the positioning information, search for repair institutions within a certain range, and then match the names of the repair institutions within the range with the words in the word list.

[0072] The first repair institution list and the second repair institution list may include at least one repair institution that cooperates with the insurance company. Specifically, the first repair institution list 5 kilometers away from the positioning information can be obtained first, and then the first similarity between the words in the word list and the institution names in the first repair institution list can be calculated based on the KNN algorithm. When the first similarity is greater than the first preset similarity, it means that there are repair institutions in the first repair institution list that meet the user's needs. When the first similarity is less than or equal to the first preset similarity, it means that there are no repair institutions in the first repair list that meet the customer's needs. At this time, the search range can be expanded to obtain a second repair institution list 10 kilometers away from the positioning information, and then the second similarity between the words in the word list and the institution names in the second repair institution list can be calculated based on the KNN algorithm. Similarly, the matching result can be determined based on the second similarity and the first preset similarity. The embodiment of the present application combines the positioning information sent by the user to search for repair institutions within a certain range from the positioning information, and then matches the names of the repair institutions within the range with the words in the word list, so that repair institutions that are closer and can meet the personalized needs of users can be recommended to customers.

[0073] In an exemplary embodiment, the method includes step S405 and step S406.

[0074] Step S405: When the second similarity is greater than the first preset similarity, the matching result is matching to the repair mechanism.

[0075] Step S406: When the second similarity is less than or equal to the first preset similarity, the matching result is that no repair organization is matched, and a repair organization at a third preset distance from the location information is determined based on the location information of the terminal device.

[0076] Exemplarily, when the second similarity between the words in the word list and the names of the institutions in the second repair institution list is greater than the first preset similarity, it indicates that the matching result is a match to a repair institution. For example, the matching result may be a match to only one repair institution or to multiple repair institutions.

[0077] When the second similarity between the words in the word list and the names of the institutions in the second repair institution list is less than or equal to the first preset similarity, it means that the matching result is that no repair institution is matched. At this time, in order to give priority to solving the customer's demand for vehicle repair, based on the location information of the user's terminal device (for example, the accident location in the input information), multiple repair institutions 1 km or 2 km away from the location information can be searched.

[0078] Step S105: Determine the target repair mechanism according to the matching result.

[0079] The embodiment of the present application needs to re-determine the target repair mechanism according to the matching result to recommend the most suitable repair mechanism to the user. For example, if the matching result is that only one repair mechanism is matched, the repair mechanism can be directly determined as the target repair mechanism; if the matching result is that multiple repair mechanisms are matched, the target repair mechanism needs to be determined from the multiple repair mechanisms.

[0080] In an exemplary implementation, step S105 includes steps S501 to S503.

[0081] S501. When the matching result is that a repair organization is matched, determine the repair organization as a target repair organization.

[0082] S502. When the matching result is that no repair organization is matched, extract the feature vectors of the input information and the case attribute information to obtain a first feature vector; input the first feature vector into a preset recommendation model so that the preset recommendation model calculates a first recommendation score for each repair organization; and determine a target repair organization based on the first recommendation score for each repair organization.

[0083] S503. When the matching result is a match to multiple repair institutions, extract the input information, the case attribute information and the feature vectors of the multiple repair institutions to obtain a second feature vector; input the second feature vector into a preset recommendation model so that the preset recommendation model calculates the second recommendation score of each repair institution, and determines the target repair institution according to the second recommendation score of each repair institution.

[0084] In the embodiment of the present application, when the matching result is a match with a repair mechanism, the repair mechanism can be determined as the target repair mechanism.

[0085] For example, the preset recommendation model in the embodiment of the present application may include the Qwen2-72B model. The Qwen2-72B model is a pre-trained and instruction fine-tuned model of the Qwen2 large model. The Qwen2-72B model can handle information extraction tasks within a 128K context length, which is of great significance for processing long texts and complex dialogue scenarios.

[0086] When the matching result is that no repair agency is matched, it means that the repair agency the user wants to go to is not a repair agency that cooperates with the insurance company. In order to comprehensively consider the actual situation of the user, the embodiment of the present application can extract the feature vector of the user's input information and the accompanying attribute information to obtain a first feature vector; for example, the first feature vector of the degree of damage to the vehicle, distance, vehicle model, insurance information, trailer, etc. Then, the first feature vector is received through the API (Application Programming Interface) and the first feature vector is input into the Qwen2-72B model. The Qwen2-72B model can calculate the first recommended score of each repair agency, and sort the first recommended scores of each repair agency from high to low, thereby selecting the repair agency with the highest first recommended score as the target repair agency.

[0087] When the matching result is that multiple repair agencies are matched, it can be explained that the repair agency that the user wants to go to is a repair agency that cooperates with the insurance company; it can also be explained that the multiple repair agencies included in the area that the user wants to go to are also repair agencies that cooperate with the insurance company. Based on this, the embodiment of the present application can extract the user's input information, the case attribute information, and the feature vectors of the matched multiple repair agencies to obtain a second feature vector; for example, the second feature vectors of A repair agency, B repair agency, C repair agency, agency service score, vehicle damage degree, vehicle model, insurance information, trailer, etc. Then, the second feature vector is received through the API and input into the Qwen2-72B model. The Qwen2-72B model can calculate the second recommended score of each matched repair agency, and sort the second recommended scores of each repair agency from high to low, so as to select the repair agency with the highest second recommended score as the target repair agency. For example, the Qwen2-72B model calculates that the score of A repair agency is 85 points, the score of B repair agency is 90 points, and the score of C repair agency is 88 points. Obviously, the score of B repair agency is the highest. Therefore, the B repair mechanism can be taken as the target repair mechanism.

[0088] The embodiment of the present application combines the user's input information, case attribute information and the feature vectors of multiple matched repair institutions, and can screen out a target repair institution that is more suitable for the user through the Qwen2-72B model, thereby improving the accuracy of repair institution recommendation.

[0089] Step S106: Send the target location information of the target repair organization to the terminal device.

[0090] After determining the target repair organization, the embodiment of the present application can send the target location information of the target repair organization via SMS. For example, the target location information of the target repair organization can be sent via SMS in the form of text or in the form of a link.

[0091] The method for recommending the location information of a repair organization provided in the above embodiment includes: obtaining input information sent by a terminal device, the input information indicating that the user needs a repair organization; obtaining the user's case attribute information; segmenting the text corresponding to the input information and the case attribute information to obtain a word list; matching the words in the word list with the organization names in a preset repair organization list to obtain a matching result, the repair organization list including at least one repair organization; determining the target repair organization according to the matching result; and sending the target location information of the target repair organization to the terminal device. The present application fully considers the user's needs and realizes personalized recommendation by segmenting the input information sent by the user and the user's case attribute information to obtain a word list, and matching the word list with the preset repair organization list. The target repair organization is determined according to the matching result, and the most suitable repair organization can be recommended to the user, thereby improving the accuracy of the recommended repair organization.

[0092] See also Figure 3 , Figure 3 This is a schematic block diagram of a repair organization location information recommendation device provided in an embodiment of the present application. The repair organization location information recommendation device can be configured in a server to execute the above-mentioned repair organization location information recommendation method.

[0093] like Figure 3 As shown, the location information recommendation device for a repair organization includes: a first acquisition module 110 , a second acquisition module 120 , a segmentation module 130 , a matching module 140 , an organization determination module 150 and a sending module 160 .

[0094] The first acquisition module 110 is used to acquire input information sent by the terminal device, where the input information indicates that the user needs a repair mechanism.

[0095] The second acquisition module 120 is used to acquire the user's case attribute information.

[0096] The segmentation module 130 is used to segment the text corresponding to the input information and the accompanying attribute information to obtain a word list.

[0097] The matching module 140 is used to match the words in the word list with the organization names in the preset repair organization list to obtain a matching result. The repair organization list includes at least one repair organization.

[0098] The mechanism determination module 150 is used to determine the target repair mechanism according to the matching result.

[0099] The sending module 160 is used to send the target location information of the target repair organization to the terminal device.

[0100] In an exemplary embodiment, the organization determination module 150 includes a first organization determination submodule, a second organization determination submodule, and a third organization determination submodule.

[0101] The first mechanism determination submodule is used to determine the repair mechanism as a target repair mechanism when the matching result is that one repair mechanism is matched.

[0102] The second institution determination submodule is used to extract the feature vectors of the input information and the case attribute information to obtain a first feature vector when the matching result is that no repair institution is matched; input the first feature vector into a preset recommendation model so that the preset recommendation model calculates a first recommendation score for each repair institution; and determine a target repair institution based on the first recommendation score for each repair institution.

[0103] The third institution determination submodule is used to extract the input information, case attribute information and feature vectors of multiple repair institutions to obtain a second feature vector when the matching result is a match to multiple repair institutions; the second feature vector is input into a preset recommendation model so that the preset recommendation model calculates the second recommendation score of each repair institution, and determines the target repair institution according to the second recommendation score of each repair institution.

[0104] In an exemplary implementation, the input information includes positioning information; the matching module includes a first acquisition submodule, a first calculation submodule, a second acquisition submodule, and a second calculation submodule.

[0105] The first acquisition submodule is used to acquire a first repair mechanism list at a first preset distance from the positioning information.

[0106] The first calculation submodule is used to calculate the first similarity between the words in the word list and the institution names in the first repair institution list based on the KNN algorithm.

[0107] The second acquisition submodule is used to acquire a second repair mechanism list at a second preset distance from the positioning information when the first similarity is less than or equal to the first preset similarity.

[0108] The second calculation submodule is used to calculate the second similarity between the words in the word list and the organization names in the second repair organization list based on the KNN algorithm, and determine the matching result according to the second similarity.

[0109] In an exemplary embodiment, the matching module further includes a first result determination submodule and a second result determination submodule.

[0110] The first result determination submodule is used to determine that the matching result is matching to the repair mechanism when the second similarity is greater than the first preset similarity.

[0111] The second result determination submodule is used to determine, when the second similarity is less than or equal to the first preset similarity, that the matching result is that no repair organization is matched, and to determine, based on the location information of the terminal device, a repair organization that is a third preset distance away from the location information.

[0112] In an exemplary embodiment, the segmentation module includes a first cleaning submodule, a word segmentation submodule and a second cleaning submodule.

[0113] The first cleaning submodule is used to perform a first cleaning process on the input information and the accompanying attribute information to obtain cleaned data.

[0114] The word segmentation submodule is used to perform word segmentation processing on the cleaned data based on a preset word segmentation algorithm to obtain word segmentation data.

[0115] The second cleaning submodule is used to perform a second cleaning process on the word segmentation data to obtain a word list.

[0116] In an exemplary embodiment, the word segmentation submodule is specifically used to construct a dictionary tree and a directed acyclic graph based on the cleaned data; based on a dynamic programming algorithm, the dictionary tree and the directed acyclic graph are searched to obtain the word segmentation data.

[0117] In an exemplary embodiment, the second cleaning submodule is specifically used to filter out words whose length is greater than a preset length in the word segmentation data to obtain first words; filter out words whose similarity is less than a second preset similarity in the first words to obtain a word list.

[0118] It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described devices and modules and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0119] The method of the present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0120] Exemplarily, the above method and apparatus may be implemented in the form of a computer program, which may be run on a computer device.

[0121] See also Figure 4 , Figure 4 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device may be a server or a terminal device.

[0122] like Figure 4 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a storage medium and an internal memory.

[0123] The storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute the steps of any one of the methods for recommending location information of a repair mechanism.

[0124] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0125] The internal memory provides an environment for the operation of the computer program in the storage medium. When the computer program is executed by the processor, the processor can execute the steps of any method for recommending location information of a repair mechanism.

[0126] The network interface is used for network communication, such as sending assigned tasks.

[0127] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0128] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0129] In one embodiment, the processor is used to execute a computer program and implement the following steps when executing the computer program:

[0130] Obtaining input information sent by the terminal device, the input information indicating that the user needs a repair organization;

[0131] Get the user's case attribute information;

[0132] Segment the text corresponding to the input information and the accompanying attribute information to obtain a word list;

[0133] Matching the words in the word list with the names of institutions in a preset repair institution list to obtain a matching result, wherein the repair institution list includes at least one repair institution;

[0134] According to the matching results, the target repair organization is determined;

[0135] The target location information of the target repair organization is sent to the terminal device.

[0136] In an exemplary embodiment, determining a target repair mechanism according to the matching result includes:

[0137] When the matching result is that a repair organization is matched, determining the repair organization as a target repair organization;

[0138] When the matching result is that no repair institution is matched, extract the feature vectors of the input information and the case attribute information to obtain a first feature vector; input the first feature vector into a preset recommendation model so that the preset recommendation model calculates a first recommendation score for each repair institution; and determine a target repair institution according to the first recommendation score for each repair institution;

[0139] When the matching result is a match to multiple repair agencies, extract the input information, case attribute information and feature vectors of multiple repair agencies to obtain a second feature vector; input the second feature vector into a preset recommendation model so that the preset recommendation model calculates the second recommendation score of each repair agency, and determines the target repair agency based on the second recommendation score of each repair agency.

[0140] In an exemplary embodiment, the input information includes positioning information; matching the words in the word list with the names of the institutions in the preset repair institution list to obtain matching results includes:

[0141] Acquire a first repair mechanism list at a first preset distance from the positioning information;

[0142] Based on the KNN algorithm, calculating the first similarity between the words in the word list and the names of the institutions in the first repair institution list;

[0143] When the first similarity is less than or equal to a first preset similarity, obtaining a second repair mechanism list at a second preset distance from the positioning information;

[0144] Based on the KNN algorithm, the second similarity between the words in the word list and the institution names in the second repair institution list is calculated, and the matching result is determined according to the second similarity.

[0145] In an exemplary implementation, determining a matching result according to the second similarity includes:

[0146] When the second similarity is greater than the first preset similarity, the matching result is matching to the repair organization;

[0147] When the second similarity is less than or equal to the first preset similarity, the matching result is that no repair organization is matched, and a repair organization at a third preset distance from the location information is determined based on the location information of the terminal device.

[0148] In an exemplary implementation, the text corresponding to the input information and the accompanying attribute information is segmented to obtain a word list, including:

[0149] Perform the first cleaning process on the input information and the attribute information accompanying the case to obtain the cleaned data;

[0150] Based on the preset word segmentation algorithm, the cleaned data is segmented to obtain the word segmentation data;

[0151] Perform a second cleaning process on the word segmentation data to obtain a word list.

[0152] In an exemplary embodiment, based on a preset word segmentation algorithm, the cleaned data is segmented to obtain the word segmentation data, including:

[0153] Construct dictionary trees and directed acyclic graphs based on cleaned data;

[0154] Based on the dynamic programming algorithm, the dictionary tree and the directed acyclic graph are searched to obtain the word segmentation data.

[0155] In an exemplary embodiment, the word segmentation data is cleaned for the second time to obtain a word list, including:

[0156] Filter out words whose length is greater than a preset length in the word segmentation data to obtain the first word;

[0157] The words whose similarity is less than the second preset similarity in the first words are filtered out to obtain a word list.

[0158] It should be noted that, those skilled in the art can clearly understand that, for the sake of convenience and brevity of description, the specific working process of recommending the location information of the above-mentioned repair organization can refer to the corresponding process in the embodiment of the aforementioned method for recommending the location information of the repair organization, and will not be repeated here.

[0159] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The method implemented when the computer program is executed by a processor can refer to the various embodiments of the location information recommendation method for the repair organization of the present application.

[0160] The computer-readable storage medium may be an internal storage unit of the computer device of the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device.

[0161] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0162] It should also be understood that the term "and / or" used in the specification of this application and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0163] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for recommending location information of a repair mechanism, characterized in that: Applicable to servers, including: Acquire input information sent by the terminal device, wherein the input information indicates that the user needs a repair mechanism; Get the user's case attribute information; Segmenting the text corresponding to the input information and the accompanying attribute information to obtain a word list; Matching the words in the word list with the names of institutions in a preset repair institution list to obtain a matching result, wherein the repair institution list includes at least one repair institution; Determining a target repair mechanism according to the matching result; The target location information of the target repair mechanism is sent to the terminal device.

2. The method for recommending location information of a repair organization according to claim 1, characterized in that: Determining a target repair mechanism according to the matching result includes: When the matching result is a match with a repair organization, determining the repair organization as a target repair organization; When the matching result is that no repair institution is matched, extract the feature vectors of the input information and the accompanying attribute information to obtain a first feature vector; input the first feature vector into a preset recommendation model so that the preset recommendation model calculates a first recommendation score for each repair institution; and determine a target repair institution according to the first recommendation score of each repair institution; When the matching result is a match to multiple repair institutions, the input information, the case attribute information and the feature vectors of the multiple repair institutions are extracted to obtain a second feature vector; the second feature vector is input into a preset recommendation model so that the preset recommendation model calculates the second recommendation score of each repair institution, and the target repair institution is determined according to the second recommendation score of each repair institution.

3. The method for recommending location information of a repair organization according to claim 1, characterized in that: The input information includes positioning information; the words in the word list are matched with the names of institutions in the preset repair institution list to obtain matching results, including: Acquire a first repair mechanism list at a first preset distance from the positioning information; Calculating, based on a KNN algorithm, a first similarity between the words in the word list and the names of the institutions in the first repair institution list; When the first similarity is less than or equal to a first preset similarity, obtaining a second repair mechanism list at a second preset distance from the positioning information; Based on the KNN algorithm, the second similarity between the words in the word list and the institution names in the second repair institution list is calculated, and the matching result is determined according to the second similarity.

4. The method for recommending location information of a repair organization according to claim 3, characterized in that: The determining a matching result according to the second similarity includes: When the second similarity is greater than the first preset similarity, the matching result is matching to a repair organization; When the second similarity is less than or equal to the first preset similarity, the matching result is that no repair organization is matched, and a repair organization at a third preset distance from the location information is determined based on the location information of the terminal device.

5. The method for recommending location information of a repair organization according to claim 1, characterized in that: The text corresponding to the input information and the accompanying attribute information is segmented to obtain a word list, including: Performing a first cleaning process on the input information and the accompanying attribute information to obtain cleansed data; Based on a preset word segmentation algorithm, the cleaned data is segmented to obtain word segmentation data; The word segmentation data is cleaned for the second time to obtain a word list.

6. The method for recommending location information of a repair organization according to claim 5, characterized in that: The word segmentation processing is performed on the cleaned data based on a preset word segmentation algorithm to obtain word segmentation data, including: Constructing a dictionary tree and a directed acyclic graph according to the cleaned data; Based on a dynamic programming algorithm, the dictionary tree and the directed acyclic graph are searched to obtain word segmentation data.

7. The method for recommending location information of a repair organization according to claim 5, characterized in that: The second cleaning process is performed on the word segmentation data to obtain a word list, including: Filter out words whose length is greater than a preset length in the word segmentation data to obtain a first word; The words whose similarity is less than a second preset similarity in the first words are filtered out to obtain a word list.

8. A device for recommending location information of a repair organization, characterized in that: Applicable to servers, including: A first acquisition module, used to acquire input information sent by the terminal device, wherein the input information indicates that the user needs a repair mechanism; The second acquisition module is used to obtain the user's case attribute information; A segmentation module, used for segmenting the text corresponding to the input information and the accompanying attribute information to obtain a word list; A matching module, used for matching the words in the word list with the names of institutions in a preset repair institution list to obtain a matching result, wherein the repair institution list includes at least one repair institution; A mechanism determination module, used to determine a target repair mechanism according to the matching result; A sending module is used to send the target location information of the target repair mechanism to the terminal device.

9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is used to execute the computer program and implement the method for recommending location information of a repair mechanism as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for recommending location information of a repair mechanism as claimed in any one of claims 1 to 7 are implemented.

Images