Data processing method and device, equipment, medium and product

Abstract

The invention provides a data processing method and device, equipment, a medium and a product. The method comprises the steps of obtaining first data; for second data belonging to unstructured data in the first data, formatting the second data by using a language model to obtain third data belonging to structured data; wherein the structured data is composed of field names and field values; updating the first data according to the third data; and presenting at least part of the updated first data in the form of the field name and the field value. In the method, the natural language processing capability of the language model is utilized to realize automatic cleaning of the data, so that efficient data consumption, data conversion and other operations are facilitated, and the data can be intuitively presented to a user in a structured form.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a data processing method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] In product sales, salespeople can identify potential customers and communicate with them in order to market products to them.

[0003] Products to be sold and potential customers often have a large amount of data, such as product-related data and customer-related data, which are usually stored in the database in the form of large text. When sales personnel perform data queries, it is difficult to obtain intuitive and clear query results. Summary of the invention

[0004] The present application provides a data processing method. The method can process data into easy-to-parse and intuitive structured data, and realize automatic data cleaning. The present application also provides a device, an electronic device, a computer-readable storage medium, and a computer program product corresponding to the above method.

[0005] In a first aspect, the present application provides a data processing method, the method comprising:

[0006] Acquire first data;

[0007] For the second data belonging to the unstructured data in the first data, formatting the second data by using the language model to obtain the third data belonging to the structured data; wherein the structured data consists of a field name and a field value;

[0008] updating the first data according to the third data;

[0009] At least part of the first data after update is presented in the form of field names and field values.

[0010] In some possible implementations, the first data includes data related to at least one object, and the method further includes:

[0011] The updated first data is associated with the at least one object and stored in a database.

[0012] In some possible implementations, storing the updated first data in a database in association with the at least one object includes:

[0013] Generate updated vector data corresponding to the first data;

[0014] The vector data is stored in a database in association with the at least one object.

[0015] In some possible implementations, the field name of the third data includes at least one of the following: a keyword characterizing a content feature of the first data, or a content identifier generated based on the content feature of the first data.

[0016] In some possible implementations, the step of formatting the second data that is unstructured data in the first data by using a language model to obtain third data that is structured data includes:

[0017] Extracting second data belonging to unstructured data from the first data;

[0018] At least the second data is sent to a language model, and third data belonging to structured data returned by the language model is received.

[0019] In some possible implementations, sending at least the second data to a language model, and receiving third data returned by the language model and belonging to structured data, includes:

[0020] At least based on the second data, a first prompt word is generated; the first prompt word is used to instruct a language model to format the second data, and the first prompt word includes at least one structured field;

[0021] The first prompt word is sent to a language model, and third data returned by the language model and belonging to structured data is received.

[0022] In some possible implementations, obtaining the first data includes:

[0023] In response to reaching the data collection time, acquiring new data between the previous data collection time and the current data collection time;

[0024] The first data is determined according to the newly added data.

[0025] In some possible implementations, the method further includes:

[0026] Receive query statements;

[0027] Determining at least one target data according to the similarity between the query statement and the data in the database;

[0028] Presenting at least part of the updated first data in the form of field names and field values ​​includes:

[0029] The at least one target data is presented in the form of field name and field value.

[0030] In some possible implementations, presenting the at least one target data in the form of a field name and a field value includes:

[0031] Classifying the at least one target data according to the target field value of the at least one target data to obtain a classification result of the at least one target data;

[0032] According to the classification result, the classification presents the object name associated with the at least one target data; and presents at least one field name of any target data in the at least one target data and the field value corresponding to the at least one field name.

[0033] In a second aspect, the present application provides a data processing device, the device comprising:

[0034] An acquisition module, used for acquiring first data;

[0035] a processing module, configured to format the second data belonging to unstructured data in the first data by using a language model to obtain third data belonging to structured data; wherein the structured data consists of a field name and a field value;

[0036] An updating module, configured to update the first data according to the third data;

[0037] A presentation module is used to present at least part of the first data after update in the form of field names and field values.

[0038] In some possible implementations, the first data includes data related to at least one object, and the apparatus further includes a storage module, wherein the storage module is configured to:

[0039] The updated first data is associated with the at least one object and stored in a database.

[0040] In some possible implementations, the storage module is specifically used to:

[0041] Generate updated vector data corresponding to the first data;

[0042] The vector data is stored in a database in association with the at least one object.

[0043] In some possible implementations, the field name of the third data includes at least one of the following: a keyword characterizing a content feature of the first data, or a content identifier generated based on the content feature of the first data.

[0044] In some possible implementations, the processing module is specifically configured to:

[0045] Extracting second data belonging to unstructured data from the first data;

[0046] At least the second data is sent to a language model, and third data belonging to structured data returned by the language model is received.

[0047] In some possible implementations, the processing module is specifically configured to:

[0048] At least based on the second data, a first prompt word is generated; the first prompt word is used to instruct a language model to format the second data, and the first prompt word includes at least one structured field;

[0049] The first prompt word is sent to a language model, and third data returned by the language model and belonging to structured data is received.

[0050] In some possible implementations, the acquisition module is specifically used to:

[0051] In response to reaching the data collection time, acquiring new data between the previous data collection time and the current data collection time;

[0052] The first data is determined according to the newly added data.

[0053] In some possible implementations, the apparatus further includes a query module, wherein the query module is configured to:

[0054] Receive query statements;

[0055] Determining at least one target data according to the similarity between the query statement and the data in the database;

[0056] The presenting module is specifically used for:

[0057] The at least one target data is presented in the form of field name and field value.

[0058] In some possible implementations, the presentation module is specifically used to:

[0059] Classifying the at least one target data according to the target field value of the at least one target data to obtain a classification result of the at least one target data;

[0060] According to the classification result, the classification presents the object name associated with the at least one target data; and presents at least one field name of any target data in the at least one target data and the field value corresponding to the at least one field name.

[0061] In a third aspect, the present application provides an electronic device, the electronic device comprising a processor and a memory. The processor and the memory communicate with each other. The processor is used to execute instructions stored in the memory, so that the electronic device performs the data processing method in the first aspect or any implementation of the first aspect.

[0062] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, wherein the instructions instruct an electronic device to execute the data processing method described in the first aspect or any one of the implementations of the first aspect.

[0063] In a fifth aspect, the present application provides a computer program product comprising instructions, which, when executed on an electronic device, enables the electronic device to execute the data processing method described in the first aspect or any one of the implementations of the first aspect.

[0064] Based on the implementations provided in the above aspects, the present application can also be further combined to provide more implementations.

[0065] It can be seen from the above technical solutions that this application has the following advantages:

[0066] The present application provides a data processing method, which first obtains first data, and formats second data that is unstructured data in the first data using a language model to obtain third data that is structured data, wherein the structured data consists of a field name and a field value. Then, based on the third data, the first data is updated, and at least part of the updated first data is presented in the form of a field name and a field value.

[0067] In this method, for the first data to be processed, the natural language processing capability of the language model is used to convert the unstructured data in the first data into structured data, and the first data is updated. In this way, the first data are all easy-to-parse and intuitive structured data, which realizes automatic data cleaning, helps to perform efficient data consumption, data conversion and other operations, and can intuitively present data to users in a structured form. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical method of the embodiments of the present application, the drawings required for use in the embodiments are briefly introduced below.

[0069] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application;

[0070] Figure 2 A flowchart of another data processing method provided in an embodiment of the present application;

[0071] Figure 3 A schematic diagram of a query page provided in an embodiment of the present application;

[0072] Figure 4 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application;

[0073] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] The terms "first" and "second" in the embodiments of the present application are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0075] First, some technical terms and application scenarios involved in the embodiments of this application are introduced.

[0076] Product sales can be understood as the process of sales personnel and customers reaching a cooperation agreement on a certain product. Specifically, product sales can include multiple project stages, such as the business opportunity confirmation stage, solution communication stage, business negotiation stage and customer signing stage.

[0077] In the business opportunity confirmation stage, sales staff can conduct preliminary communication with customers to confirm that customers are willing to learn more about the product and have potential intentions. In the solution communication stage, sales staff can demonstrate the solution to key customers and introduce the product and related information in detail. In the business negotiation stage, sales staff can negotiate with customers to confirm specific information such as the purchase quantity and price of the product. In the customer signing stage, sales staff can sign a contract with customers and reach a cooperation agreement.

[0078] In each project stage of product sales, sales personnel often need to consult a large amount of data. For example, in the business opportunity confirmation stage, sales personnel need to consult customer-related data to understand the customer's industry, customer size and other data, so as to have an in-depth understanding of the customer and promote products to the customer in a more targeted manner. For another example, in the solution communication stage and business negotiation stage, sales personnel need to consult product-related data to understand product functions, product features and other data, so as to fully introduce the product to the customer and improve the success rate of cooperation. For another example, in the customer contract signing stage, sales personnel need to query historical product sales records to understand the historical contract signing data of the same product or the historical contract signing data of the same type of customers, so as to formulate a more reasonable contract.

[0079] The above data related to product sales are usually stored in the database in the form of large texts. Sales personnel can query the data through rule matching or regular extraction. Specifically, in the rule matching method, sales personnel can pre-formulate query rules related to keywords, phrases, grammatical structures, etc., and apply the query rules in the database to obtain query results. In the regular extraction method, sales personnel can construct regular expressions, execute the regular expressions in the database, and obtain query results.

[0080] When using the above method to query data, it is often difficult to obtain intuitive and clear query results. Since the query results are often a paragraph or a few sentences in a large document, sales personnel can only learn the content of the query results by viewing the query results, but cannot learn other information related to the query results. For example, when the query results are a few sentences in a document, sales personnel can only understand these sentences by viewing the query results, but cannot understand the contextual information such as the specific products, specific customers, and specific sales scenarios involved in the query results.

[0081] In scenarios where data query efficiency is not high, the above method of data query can meet the query needs. However, sales staff and customers often communicate through telephone, video conference and other communication methods. Sales staff do not have enough time to query data for customer questions. In the above scenarios where data query efficiency is high, if rule matching or regular extraction is used for data query, sales staff also need to manually check the document where the query result is located to obtain context information, which is inefficient.

[0082] In view of this, the present application provides a data processing method. The method first obtains first data, and formats the second data that is unstructured data in the first data using a language model to obtain third data that is structured data, wherein the structured data consists of a field name and a field value, and then updates the first data according to the third data, and presents at least part of the updated first data in the form of a field name and a field value.

[0083] In this method, for the first data to be processed, the natural language processing capability of the language model is used to convert the unstructured data in the first data into structured data, and the first data is updated. In this way, the first data are all easy-to-parse and intuitive structured data, which realizes automatic data cleaning, helps to perform efficient data consumption, data conversion and other operations, and can intuitively present data to users in a structured form.

[0084] To facilitate understanding of the technical solution provided by the embodiments of the present application, it will be described below with reference to the accompanying drawings.

[0085] See also Figure 1The flowchart of a data processing method provided by an embodiment of the present application is shown, and the method specifically includes:

[0086] S101: Acquire first data.

[0087] Among them, the first data can be understood as data that needs to be processed. In some possible implementations, the first data can come from a business system. In other words, the first data can include business data of different businesses. The data processing method provided in the embodiment of the present application can process business data of different business systems. In the product sales scenario, the business system can be a customer service management (CSM) system, and the first data can be customer-related data or product-related data.

[0088] In some embodiments, the first data may be acquired periodically. Specifically, in response to reaching the data acquisition time, newly added data between the previous data acquisition time and the current data acquisition time is acquired, and the first data is determined based on the newly added data.

[0089] The data collection time usually refers to the time when data collection is performed. In some possible implementations, a data collection task is set to be executed regularly, and the execution time of the data collection task is the arrival time of data collection. For example, a regularly executed data collection task may be a data collection task executed at 9 pm every day. In this case, the data collection time may be 9 pm every day.

[0090] The current data collection time can be understood as the data collection time currently being executed for acquiring the first data, and the previous data collection time can be understood as the data collection time adjacent to the current data collection time. For example, when the data collection time is 9 o'clock every evening, the current data collection time is 9 o'clock on the Tth day, and the previous data collection time is 9 o'clock on the T-1st day, where T is a natural number greater than 1.

[0091] In the embodiment of the present application, data is acquired periodically, and new data between two data acquisition moments is used as the first data to be processed, so that the new data can be quickly and regularly acquired and processed.

[0092] When the first data includes business data of different businesses, the new business data of each business can be processed in a timely manner by regularly acquiring data, thereby improving business operation efficiency.

[0093] S102: For the second data that is unstructured data in the first data, format the second data using a language model to obtain third data that is structured data.

[0094] Among them, structured data and unstructured data can be understood as different ways of storing and organizing data. Structured data has a clear data model defined, usually presented in the form of fields, that is, structured data can be composed of field names and field values, which is easy to query and analyze. Unstructured data does not have a clear data model defined, and the content and format of the data are diverse, which is not easy to query and analyze.

[0095] The first data may include some data that is structured data and some data that is unstructured data. It is understandable that since the first data may include business data of different businesses, and business data may have different forms of expression, the first data may include some data that is unstructured data. For example, in a product sales scenario, a customer proposal written by a salesperson may be unstructured data.

[0096] In an embodiment of the present application, part of the first data that is unstructured data is referred to as second data, and is formatted with the aid of a language model, wherein the formatting process can be understood as a process of converting unstructured data into structured data.

[0097] In a specific implementation, second data belonging to unstructured data is extracted from the first data, the second data is at least sent to a language model, and third data belonging to structured data returned by the language model is received.

[0098] That is to say, firstly, the data type of the first data is identified, structured data and unstructured data are extracted from the first data, and then the language model is used to process the second data that needs to be formatted, and the second data is converted into structured data.

[0099] The language model has natural language processing capabilities, can recognize, analyze, and generate natural language content, and can handle different types of natural language tasks. For example, the language model can be a deep learning model trained using text data.

[0100] That is to say, since the second data usually represents natural language content and does not have a clear data model or data format, does not have clear fields, and is difficult to convert the format through field extraction and the like, the embodiment of the present application utilizes the natural language processing capabilities of the natural language model to identify the content of the second data and convert the second data into structured data.

[0101] In a specific implementation, a first prompt word is generated based on at least the second data, the first prompt word is sent to the language model, and third data returned by the language model and belonging to structured data is received. The first prompt word is used to instruct the language model to format the second data, and the first prompt word includes at least one structured field.

[0102] That is to say, in the embodiment of the present application, format conversion is achieved based on prompt learning. Among them, prompt words can be used to guide the language model to perform specific output in generative tasks (such as text generation tasks, question-answering tasks, and dialogue tasks). By generating prompt words, the language model is helped to understand the background and requirements of the task, so that the language model can handle different types of natural language processing tasks without retraining the language model, thereby increasing the scalability and flexibility of the language model.

[0103] In the embodiment of the present application, the first prompt word may include the second data, at least one structured field, and an instruction for formatting (i.e., converting to structured data containing at least one structured field), and through the prompt capability of the first prompt word, the language model is instructed to format the second data to generate third data belonging to structured data. In this way, unstructured data is automatically converted to structured data.

[0104] To illustrate with a specific example, in a product sales scenario, the second data includes a customer plan written by a salesperson. In this case, at least one structured field in the first prompt word may include a "pain point" field, a "solution" field, and a "related document" field. Through the prompt capability of the first prompt word, the language model formats the second data and converts the customer plan, which is unstructured data, into structured data including a "pain point" field, a "solution" field, and a "related document" field.

[0105] In an embodiment of the present application, the field name of the third data returned by the language model may include at least one of the following: a keyword representing a content feature of the first data, or a content identifier generated based on the content feature of the first data.

[0106] That is, the content of the first data is analyzed by the language model, and keywords in the first data are extracted as field names, or content identifiers are summarized as field names based on the content represented by the first data. In this way, the third field generated after formatting can express the content of the first data as a whole and comprehensively through the field name.

[0107] S103: Update the first data according to the third data.

[0108] In the embodiment of the present application, after the second data belonging to the unstructured data is converted into the third data belonging to the structured data, the first data can be updated. Specifically, the second data in the first data can be replaced by the third data, so that the first data no longer includes the unstructured data, but is all structured data.

[0109] In some embodiments, the updated first data may be stored in a database. In a specific implementation, the first data may include data related to at least one object, and the updated first data is associated with the at least one object and stored in a database.

[0110] Here, an object can be understood as an entity related to the business. For example, in a product sales scenario, an object can be a customer, an organization, a product, a service, etc.

[0111] Associative storage can be understood as an association relationship between data and objects in a database. In an embodiment of the present application, objects related to data are indicated by associative storage. For example, the updated first data includes data A, data B, and data C, and data A, data B, and data C are all structured data. Data A and data B are data related to product A, and data C is data related to product B. When the updated first data is stored in the database, data A is stored in association with product A, data B is stored in association with product A, and data C is stored in association with product B. In this way, it is indicated that the data related to product A includes data A and data B, and the data related to product B includes data C.

[0112] In an embodiment of the present application, the collected data is cleaned into structured data before being stored in the database. In this way, all the data in the database are structured data, which helps to improve the efficiency of subsequent data consumption.

[0113] In some possible implementations, the updated first data may be stored in the form of vector data. Specifically, vector data corresponding to the updated first data is generated, and the vector data is associated with at least one object and stored in a database.

[0114] The vector data may be understood as data obtained by vectorizing the updated first data. Generally, feature extraction may be performed on the updated first data, and the extracted features may be converted into numerical vectors (ie, vector data) that can represent data in a vector space.

[0115] In this way, the updated first data is stored in a vector database. Since vector data has a more flexible data representation, it saves storage space, reduces data storage redundancy, and improves storage stability for scenarios that require storage of large amounts of business data.

[0116] S104: Present at least a portion of the updated first data in the form of field names and field values.

[0117] In an embodiment of the present application, after unstructured data is converted into structured data, the data can be presented to the user more intuitively in a structured form of field names and field values.

[0118] For example, the updated first data includes data A and data B, both of which are structured data, data A includes field name 1 and field value 1, field name 2 and field value 2, and data B includes field name 3 and field value 3. When data A is presented in the form of field name and field value, "field name 1: field value 1" and "field name 2: field value 2" may be presented, and when data B is presented in the form of field name and field value, "field name 3: field value 3" may be presented.

[0119] In some possible implementations, data can be presented based on a data query operation triggered by a user in a database. Figure 2 The flow chart of the data processing method shown in the figure, in the data processing link, the first data is obtained, the second data belonging to the unstructured data in the first data is formatted using the language model, the third data belonging to the structured data is obtained, and the first data is updated according to the third data, and then the updated first data belonging to the structured data is stored in the database.

[0120] In the data consumption link, a query statement is received, at least one target data is determined according to the similarity between the query statement and the data in the database, and the at least one target data is presented in the form of a field name and a field value.

[0121] Among them, the query statement (query) can be understood as a statement used to query data in a database. In an embodiment of the present application, a user can enter a query statement to query data. For example, in a product sales scenario, when a salesperson needs to query data about product A, he can enter a query statement for querying data related to product A to trigger a data query operation.

[0122] The at least one target data may be understood as data in the database whose similarity with the query statement satisfies a set condition (for example, the similarity is greater than a set threshold), that is, structured data that is relatively similar to the query statement.

[0123] In some embodiments, the updated first data is stored in the database in the form of vector data. In this case, feature extraction is performed on the query statement, and the extracted features are converted into vector representations. The distance between the vector data in the database and the vector representation of the query statement is used to characterize the similarity between the data in the database and the query statement, and then the data whose similarity meets the query conditions is determined as the target data to complete the data query.

[0124] Furthermore, since the data is structured and cleaned before being stored in the database in the embodiment of the present application, the target data is structured data. After determining at least one target data, the target data is presented to the user in the form of field name and field value, so that when the user views the query results, he can grasp the key points intuitively and clearly, and the data query efficiency is high.

[0125] Furthermore, considering that the first data in the database may be related to at least one object, when presenting the query results, the query results may be presented in different dimensions and in a diversified manner. Specifically, at least one target data is classified according to the target field value of at least one target data to obtain the classification result of at least one target data, and then, according to the classification result, the object name associated with at least one target data is presented in a classified manner, and at least one field name of any target data in at least one target data and the field value corresponding to the at least one field name are presented.

[0126] That is to say, after the query statement is queried, there may be multiple target data obtained by the query, and the display effect of presenting the target data in the form of field names and field values ​​is poor. Therefore, the target data can be classified by the target data value, and the object names associated with the target data can be presented in the classification. In this way, the user can have an overall understanding of the query results through the object names presented in the classification.

[0127] Furthermore, any target data in at least one target data (for example, target data related to the object name triggered by the user) is presented in the form of field name and field value. In this way, multi-dimensional and rich data is presented in a limited presentation area, which increases the amount of information and presents it in a structured form, thereby optimizing the experience of viewing query results.

[0128] In this method, for the first data to be processed, the natural language processing capability of the language model is used to convert the unstructured data in the first data into structured data, and the first data is updated. In this way, the first data are all easy-to-parse and intuitive structured data, which realizes automatic data cleaning, helps to perform efficient data consumption, data conversion and other operations, and can intuitively present data to users in a structured form.

[0129] The following is an explanation based on the specific query page.

[0130] See also Figure 3 The schematic diagram of the query page shown in the figure includes a query area 301 and query result presentation areas 302 and 303. A user (e.g., a salesperson) can enter a query statement in the query area 301, such as "finance", and click the query control to trigger a query operation.

[0131] In response to the query operation, at least one target data is determined according to the similarity between the query statement and the data in the database, and the object name associated with the at least one target data is presented in a classified manner in the query result presentation area 302. In this example, the target field value is the enterprise scale, and the at least one target data is classified based on the "enterprise scale", and the classification result obtained is: the enterprise scale of enterprise A is 10000 to 99999, the enterprise scale of enterprise B and enterprise C is 3000 to 4999, and the enterprise scale of enterprise D, enterprise E and enterprise F is 1000 to 2999. In this way, according to the classification result, the object name (i.e., enterprise name) associated with the at least one target data is presented in a classified manner.

[0132] Furthermore, in the city and county area 303 of the query result, any target data is presented in the form of field name and field value. In this example, the target data includes "case of winning orders", "project situation overview" data and "policy evaluation" data. Among them, the "case of winning orders" data is structured data and can be stored in the database without formatting, and the "project situation overview" data and "policy evaluation" data are unstructured data. After the "project situation overview" data and "policy evaluation" data are formatted using a language model, the "project situation overview" data and "policy evaluation" data are converted into structured data containing "pain point" fields and "solution" fields. In this way, when the query results are presented in the query result presentation area 303, the "project situation overview" data and "policy evaluation" data are presented in the form of field values ​​and field names.

[0133] In an embodiment of the present application, by performing a pre-processing operation to format the data, it is ensured that the data stored in the database are all structured data, and during the data query process, the target data can be presented to the user in a structured form. In this way, the user can quickly understand the context information of the target data by viewing the field name and field value of the target data, without having to manually view the target data, thereby improving data query efficiency. In a product sales scenario, through the data processing method provided in an embodiment of the present application, the business data is structured and stored, and when the salesperson communicates with the customer, the salesperson can perform efficient data query, meet the scenario with high data query efficiency, quickly respond to customer questions, and improve communication efficiency.

[0134] Combination of the above Figures 1 to 3 The data processing method provided in the embodiment of the present application is introduced in detail. The device and equipment provided in the embodiment of the present application will be introduced in conjunction with the accompanying drawings.

[0135] See also Figure 4 The structural diagram of the data processing device shown in FIG. 40 includes:

[0136] An acquisition module 401 is used to acquire first data;

[0137] The processing module 402 is used to format the second data belonging to unstructured data in the first data by using a language model to obtain third data belonging to structured data; wherein the structured data consists of a field name and a field value;

[0138] An updating module 403, configured to update the first data according to the third data;

[0139] The presentation module 404 is used to present at least part of the first data after update in the form of field names and field values.

[0140] In some possible implementations, the first data includes data related to at least one object, and the apparatus further includes a storage module, wherein the storage module is configured to:

[0141] The updated first data is associated with the at least one object and stored in a database.

[0142] In some possible implementations, the storage module is specifically used to:

[0143] Generate updated vector data corresponding to the first data;

[0144] The vector data is stored in a database in association with the at least one object.

[0145] In some possible implementations, the field name of the third data includes at least one of the following: a keyword characterizing a content feature of the first data, or a content identifier generated based on the content feature of the first data.

[0146] In some possible implementations, the processing module 402 is specifically configured to:

[0147] Extracting second data belonging to unstructured data from the first data;

[0148] At least the second data is sent to a language model, and third data belonging to structured data returned by the language model is received.

[0149] In some possible implementations, the processing module 402 is specifically configured to:

[0150] At least based on the second data, a first prompt word is generated; the first prompt word is used to instruct a language model to format the second data, and the first prompt word includes at least one structured field;

[0151] The first prompt word is sent to a language model, and third data returned by the language model and belonging to structured data is received.

[0152] In some possible implementations, the acquisition module 401 is specifically used to:

[0153] In response to reaching the data collection time, acquiring new data between the previous data collection time and the current data collection time;

[0154] The first data is determined according to the newly added data.

[0155] In some possible implementations, the apparatus further includes a query module, wherein the query module is configured to:

[0156] Receive query statements;

[0157] Determining at least one target data according to the similarity between the query statement and the data in the database;

[0158] The presenting module 404 is specifically used for:

[0159] The at least one target data is presented in the form of field name and field value.

[0160] In some possible implementations, the presenting module 404 is specifically configured to:

[0161] Classifying the at least one target data according to the target field value of the at least one target data to obtain a classification result of the at least one target data;

[0162] According to the classification result, the classification presents the object name associated with the at least one target data; and presents at least one field name of any target data in the at least one target data and the field value corresponding to the at least one field name.

[0163] The data processing device 40 according to the embodiment of the present application may correspond to executing the method described in the embodiment of the present application, and the above and other operations and / or functions of each module / unit of the data processing device 40 are respectively to implement Figure 1 For the sake of brevity, the corresponding processes of each method in the illustrated embodiment are not described in detail here.

[0164] The present application also provides an electronic device. The electronic device is specifically used to implement Figure 4 The functionality of the data processing device 40 in the illustrated embodiment.

[0165] Figure 5 A schematic diagram of the structure of an electronic device 500 is provided. Figure 5 As shown, the electronic device 500 includes a bus 501, a processor 502, a communication interface 503 and a memory 504. The processor 502, the memory 504 and the communication interface 503 communicate with each other via the bus 501.

[0166] The bus 501 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0167] The processor 502 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0168] The communication interface 503 is used for communicating with the outside. For example, the communication interface 503 can be used for communicating with a terminal.

[0169] The memory 504 may include a volatile memory, such as a random access memory (RAM). The memory 504 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0170] The memory 504 stores executable codes, and the processor 502 executes the executable codes to perform the aforementioned data processing method.

[0171] Specifically, in implementing Figure 4In the case of the embodiment shown, and Figure 4 When each module or unit of the data processing device 40 described in the embodiment is implemented by software, the execution Figure 4 The software or program code required for the functions of each module / unit in the system may be partially or completely stored in the memory 504. The processor 502 executes the program code corresponding to each unit stored in the memory 504 to perform the aforementioned data processing method.

[0172] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the computing device to execute the data processing method applied to the data processing device 40.

[0173] The embodiment of the present application further provides a computer program product, which includes one or more computer instructions. When the computer instructions are loaded and executed on a computing device, the process or function described in the embodiment of the present application is generated in whole or in part.

[0174] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer or data center to another website, computer or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0175] When the computer program product is executed by a computer, the computer executes any of the aforementioned data processing methods. The computer program product may be a software installation package, and when any of the aforementioned data processing methods is needed, the computer program product may be downloaded and executed on a computer.

[0176] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to each embodiment of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0177] The units involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the unit / module does not, in some cases, constitute a limitation on the unit itself.

[0178] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0179] In the context of the present application embodiment, machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable medium can include but is not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the above. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0180] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the system or device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0181] 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.

[0182] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device 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 device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0183] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0184] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data processing method, characterized in that: The method comprises: Acquire first data; For the second data belonging to the unstructured data in the first data, formatting the second data by using the language model to obtain the third data belonging to the structured data; wherein the structured data consists of a field name and a field value; updating the first data according to the third data; At least part of the first data after update is presented in the form of field names and field values.

2. The method according to claim 1, characterized in that The first data includes data related to at least one object, and the method further includes: The updated first data is associated with the at least one object and stored in a database.

3. The method according to claim 2, characterized in that The step of associating the updated first data with the at least one object and storing them in a database comprises: Generate updated vector data corresponding to the first data; The vector data is stored in a database in association with the at least one object.

4. The method according to claim 1, characterized in that: The field name of the third data includes at least one of the following: a keyword representing a content feature of the first data, or a content identifier generated based on the content feature of the first data.

5. The method according to claim 1, characterized in that The step of formatting the second data that is unstructured data in the first data by using a language model to obtain third data that is structured data includes: Extracting second data belonging to unstructured data from the first data; At least the second data is sent to a language model, and third data belonging to structured data returned by the language model is received.

6. The method according to claim 5, characterized in that The at least sending the second data to the language model and receiving the third data returned by the language model and belonging to the structured data comprises: At least based on the second data, a first prompt word is generated; the first prompt word is used to instruct a language model to format the second data, and the first prompt word includes at least one structured field; The first prompt word is sent to a language model, and third data returned by the language model and belonging to structured data is received.

7. The method according to any one of claims 1 to 6, characterized in that: The obtaining of the first data comprises: In response to reaching the data collection time, acquiring new data between the previous data collection time and the current data collection time; The first data is determined according to the newly added data.

8. The method according to claim 2, characterized in that: The method further comprises: Receive query statements; Determining at least one target data according to the similarity between the query statement and the data in the database; Presenting at least part of the updated first data in the form of field names and field values ​​includes: The at least one target data is presented in the form of field name and field value.

9. The method according to claim 8, characterized in that The presenting of the at least one target data in the form of a field name and a field value includes: Classifying the at least one target data according to the target field value of the at least one target data to obtain a classification result of the at least one target data; According to the classification result, the classification presents the object name associated with the at least one target data; and presents at least one field name of any target data in the at least one target data and the field value corresponding to the at least one field name.

10. A data processing device, characterized in that: The device comprises: An acquisition module, used for acquiring first data; a processing module, configured to format the second data belonging to unstructured data in the first data by using a language model to obtain third data belonging to structured data; wherein the structured data consists of a field name and a field value; An updating module, configured to update the first data according to the third data; A presentation module is used to present at least part of the first data after update in the form of field names and field values.

11. An electronic device, characterized in that: The electronic device comprises a processor and a memory; The processor is configured to execute instructions stored in the memory, so that the electronic device performs the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The method comprises instructions, wherein the instructions instruct an electronic device to execute the method as claimed in any one of claims 1 to 9.

13. A computer program product, characterized in that The computer program product comprises computer readable instructions for implementing the method according to any one of claims 1 to 9.

Images