Information query method, device, computer equipment and medium

Abstract

Embodiments of the present invention disclose an information query method, apparatus, computer equipment, and medium. The method includes, in response to a query voice input by an industrial user, obtaining a query keyword and a target dialect type that match the query voice; obtaining a target industrial order that matches the query keyword from each industrial order; determining target region information that matches the industrial user based on the target dialect type; filtering query result information from each target industrial order based on the geographic location information and target region information of the publisher included in each target industrial order, and feeding the query result information back to the industrial user. While solving the problem of practitioners having difficulty using text input methods through language input, it saves search time and improves search efficiency.

Description

Technical Field

[0001] The embodiments of the present invention relate to computer data processing technology, and more particularly to an information query method, apparatus, computer equipment, and medium. Background Art

[0002] With the continuous development of intelligent manufacturing technology, electronic trading platforms in the field of industrial manufacturing have emerged. Users can publish various leasing orders or rental orders for industrial equipment on the electronic trading platform, and can also publish production orders for various industrial manufacturing products on the electronic trading platform.

[0003] Considering the typically enormous amount of information posted on electronic trading platforms, prior art techniques typically involve users logging into the platform and searching for their actual needs. For example, searching for specific industrial equipment rental needs or specific industrial manufacturing product supply needs, they then search the platform to identify the industrial orders they are interested in amidst the vast array of industrial order information. Furthermore, using the electronic trading platform as a medium, the diverse order needs of different users in various industrial manufacturing fields can be met.

[0004] While developing this invention, the inventors discovered the following drawbacks in the existing technology: When users wish to accurately and efficiently search for desired industrial orders on electronic trading platforms, they typically must add search keywords or manually filter information. These methods are labor-intensive and time-consuming. In particular, users unfamiliar with the specific functions of electronic trading platforms or the operation of electronic devices cannot quickly filter out the desired information. Summary of the Invention

[0005] The embodiments of the present invention provide an information query method, apparatus, computer equipment, and medium to improve voice search efficiency and save search time.

[0006] In a first aspect, an embodiment of the present invention provides an information query method, which is executed by an electronic trading platform in the field of industrial manufacturing, comprising:

[0007] In response to a query voice input by an industrial user, obtaining a query keyword and a target dialect type that match the query voice;

[0008] Obtaining target industrial orders matching the query keyword from various industrial orders;

[0009] Determining target region information matching the industrial user according to the target dialect type;

[0010] According to the geographic location information of the publisher included in each target industrial order and the target region information, query result information is screened in each target industrial order, and the query result information is fed back to the industrial user.

[0011] In a second aspect, an embodiment of the present invention further provides an information query device, the information query device comprising:

[0012] A query keyword and target dialect type acquisition module, configured to respond to a query voice input by an industrial user and acquire a query keyword and a target dialect type that match the query voice;

[0013] A target industrial order acquisition module is used to acquire target industrial orders that match the query keyword from various industrial orders;

[0014] A target region information determination module, configured to determine target region information matching the industrial user according to the target dialect type;

[0015] The query result information feedback module is used to filter the query result information in each target industrial order according to the geographic location information of the publisher and the target region information included in each target industrial order, and feed back the query result information to the industrial user.

[0016] In a third aspect, an embodiment of the present invention further provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the information query method as described in any embodiment of the present invention is implemented.

[0017] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the information query method as described in any embodiment of the present invention.

[0018] The technical solution provided by the embodiment of the present invention obtains query keywords and target dialect types that match the query voice in response to the query voice input by the industrial user; obtains target industrial orders that match the query keywords from various industrial orders; determines target region information that matches the industrial user based on the target dialect type; and filters query result information from each target industrial order based on the geographic location information of the publisher and the target region information included in each target industrial order, and feeds back the query result information to the industrial user. The technical solution of the embodiment of the present invention not only analyzes the language content in the query voice of the industrial user, but also further analyzes the dialect type of the query voice, and then can quickly filter out the information actually needed by the industrial user through the platform in combination with the dialect type. While solving the problem of practitioners having difficulty using text input methods through language input, it further saves search time and improves search efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flowchart of an information query method provided by an embodiment of the present invention;

[0020] Figure 2 A flowchart of another information query method provided by an embodiment of the present invention;

[0021] Figure 3 A flowchart of another information query method provided by an embodiment of the present invention;

[0022] Figure 4 A schematic diagram of the structure of an information query device provided by an embodiment of the present invention;

[0023] Figure 5 A schematic structural diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0025] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0026] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0027] It should be noted that the concepts of "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0028] It should be noted that the modifications of "one" and "multiple" mentioned in the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0029] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0030] Embodiments of the present invention can query information on computer systems implemented using artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0031] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0032] Figure 1 This is a flowchart of an information query method provided by an embodiment of the present invention. This embodiment is applicable to industrial users in the industrial manufacturing field, who use intelligent voice assistants to obtain query result information in the region where the industrial users are located in an electronic trading platform. The method of this embodiment can be executed by an information query device, which can be implemented in software and / or hardware. The device can be configured in an electronic trading platform equipped with an intelligent voice assistant. Figure 1 As shown, the method specifically includes the following steps:

[0033] S110 . In response to a query voice input by an industrial user, obtain query keywords and a target dialect type that match the query voice.

[0034] The electronic trading platform in the industrial manufacturing sector is a standardized service platform that provides industrial users with the ability to publish and query industrial orders. Industrial users can use the electronic trading platform to place various lease or rental orders for industrial equipment, as well as production orders for various industrial manufacturing products.

[0035] The lease order typically includes the type of industrial equipment to be leased (e.g., model or name), the lease period, and the equipment's geographic location. The rental order typically includes the type of equipment to be leased, the lease period, and the lessee's geographic location. The production order typically includes the model (or name), quantity, and delivery date of the industrial product being leased.

[0036] Correspondingly, industrial users who have set leasing needs for industrial equipment (the corresponding demand order is a leasing order), leasing needs (the corresponding demand order is a leasing order) and supply needs can log in to the electronic trading platform and obtain the required industrial orders from various industrial order queries.

[0037] In this embodiment, an intelligent voice assistant is integrated into the electronic trading platform. The intelligent voice assistant can not only help industrial users to realize voice query search, but also can evoke corresponding service functions in the electronic trading platform through user voice, such as query function, information release function or order tracking function, etc., eliminating the need for industrial users to perform search operations.

[0038] Specifically, when building the intelligent voice assistant, the dialect, region, industrial manufacturing field proper nouns, and industry common names and nicknames data input into the electronic trading platform can be sorted as sample data, and then the sample data is divided into sample sets, 80% of which are used to train the intelligent voice recognition model, and the remaining 20% ​​of the data are used as a test set. The model is then further output through conventional preprocessing, network design, and optimization algorithms, and the model is then verified using the data from the test set until the model accuracy reaches 90%. Different types of dialects and field proper nouns can be used for continuous adjustment during the training process.

[0039] Accordingly, industrial users who do not have proficiency in operating electronic trading platforms or electronic products can also use intelligent voice assistants to input voice commands to activate the query function of the electronic trading platform and enter corresponding query voice.

[0040] By performing recognition processing on the query speech, one or more query keywords and the target dialect type corresponding to the query speech can be obtained from the query speech.

[0041] The query keyword can be a keyword that reflects the user's actual query intent and is generally used as an industrial order query condition. Typically, the query keyword includes a target query object, or query subject, such as the name or model of the industrial equipment to be leased corresponding to the user's rental order query requirement.

[0042] Target dialect types include: Mandarin, Gan dialect, Wu dialect, Xiang dialect, Cantonese dialect, Hakka dialect, and Min dialect. Mandarin dialects can also be further divided into North China Mandarin, Northwest Mandarin, Southwest Mandarin, and Jianghuai Mandarin. It is understandable that the dialect type of an industrial user can, to a certain extent, reflect the region in which the industrial user is currently located. The two are strongly correlated. By analyzing the dialect type corresponding to the industrial user, the geographical location of the industrial user can be indirectly determined, thereby providing more accurate industrial orders for the industrial user.

[0043] In this embodiment, a dialect recognition model can be pre-trained, the input of which is speech, and the output of which is the target dialect type to which the speech belongs. Alternatively, if the dialect recognition model is a multi-classification model, the output can be the probability value of the speech belonging to each dialect type, and then the dialect type with the largest probability value can be selected as the target dialect type.

[0044] Optionally, determining the target region information matching the industrial user based on the target dialect type may include: querying a first mapping relationship between the dialect type and region information, and acquiring the target region information matching the target dialect type based on the first mapping relationship.

[0045] The first mapping relationship may be a mapping relationship between a dialect type and region information. Specifically, one dialect type corresponds to one or more region information.

[0046] For example, assuming that the dialect type used by an industrial user is the Tianjin dialect, when the user performs a voice query, such as "query for industrial equipment for manufacturing toys", the intelligent voice assistant can obtain the user's query keyword as "industrial equipment for manufacturing toys" and can identify that the user's dialect type is the Tianjin dialect. When it is determined that the user's dialect type is the Tianjin dialect, the target regional information matching the target dialect type can be obtained based on the first mapping relationship between the query dialect type and the regional information. Specifically, it can be known that the target regional information corresponding to the Tianjin dialect used by the user is Tianjin, thereby determining the user's regional information.

[0047] The advantage of this setting is that: based on the first mapping relationship between the dialect type and the regional information, the user's regional information can be further determined according to the dialect used by the user, so that the user's regional information can be used as the query center, and a search that meets the query keywords can be performed in the vicinity of the user's regional information, thereby obtaining corresponding search results for the user to choose.

[0048] Optionally, determining the target regional information matching the industrial user based on the target dialect type includes: obtaining platform login information corresponding to the industrial user, and obtaining target enterprise registration location information and target permanent residence information matching the industrial user based on the platform login information; inputting the industrial user's target enterprise registration location information, target permanent residence information and the target dialect type into a pre-trained regional recognition model to obtain the target regional information matching the industrial user.

[0049] The platform login information may include the login account information and user attribute information used by the industrial user to log in to the electronic trading platform, and may specifically include the user's account information and login location. Generally speaking, when an industrial user registers their account information, they will also enter the registered location information of the industrial user's company on the electronic trading platform.

[0050] Correspondingly, the target enterprise registration location information may be detailed information on the registration location of the enterprise to which the industrial user currently inputting the query language belongs. The target permanent location information may be geographical location information where the user frequently appears.

[0051] The regional identification model can be a model that can determine the geographical location of the industrial user after inputting the target enterprise registration information, target permanent residence information and the target dialect type of the industrial user, that is, a machine learning model that can obtain the target regional information matching the industrial user.

[0052] For example, assuming the dialect used by an industrial user is Tianjin dialect, when the user performs a voice query, such as "search for industrial equipment for toy manufacturing," the corresponding query keyword can be found, and the user's dialect type can be identified as Tianjin dialect. At the same time, it is necessary to obtain the platform login information corresponding to the industrial user, and based on the platform login information, obtain the target enterprise registration location information and target permanent residence information that match the industrial user. Specifically, the target enterprise registration location information that matches the industrial user is Beijing, and the target permanent residence information is Tianjin.

[0053] Furthermore, the target enterprise registration location information of the industrial user as Beijing, the target permanent location information as Tianjin, and the target dialect type as Tianjin dialect can be input into the pre-trained regional recognition model to obtain the target regional information output by the regional recognition model that matches the industrial user, namely Tianjin.

[0054] Specifically, although the company's registered place information is Beijing, the target permanent place information is Tianjin and the target dialect type is Tianjin dialect. After learning using multiple training samples, the regional recognition model can determine that the probability of the company's industrial equipment production site being in Tianjin is relatively high, and then can output Tianjin as the model output result.

[0055] The benefit of this setup is that by obtaining the target enterprise registration location, target permanent location, and target dialect type that match the industrial user, and inputting this information into a pre-trained region recognition model, the target region information matching the industrial user is obtained. This allows for accurate determination of target region information using comprehensive information, resulting in more accurate search results, making it easier for industrial users to operate and improving search efficiency.

[0056] S120: Obtain target industrial orders matching the query keyword from various industrial orders.

[0057] As mentioned above, different industrial users can publish industrial orders in the electronic trading platform at different times, and different types of industrial orders correspond to different industrial needs.

[0058] The target industrial order may be an industrial order screened out from various industrial orders stored locally on the electronic trading platform by searching using query keywords.

[0059] For example, assuming that the dialect type used by the industrial user is Tianjin dialect, when the user makes a voice query, for example, the user says "query industrial equipment for manufacturing toys", the intelligent voice assistant can obtain the user's query keyword as "industrial equipment for manufacturing toys", and can recognize that the user's dialect type is Tianjin dialect. Then the electronic trading platform can obtain the target industrial orders that match the query keywords from the various industrial orders stored locally. Assume that there are a total of 100 industrial orders published on the electronic trading platform, of which 30 are industrial orders for "industrial equipment for manufacturing toys". Accordingly, 30 target industrial orders that match the query keyword "industrial equipment for manufacturing toys" can be screened out.

[0060] S130: Determine target region information matching the industrial user according to the target dialect type.

[0061] Continuing with the previous example, based on the fact that the dialect used by the industrial user is Tianjin dialect, it can be further determined that the region information of the industrial user is Tianjin, that is, the target region information is Tianjin.

[0062] S140 , based on the geographic location information of the publisher included in each target industrial order and the target region information, filter each target industrial order to obtain query result information, and feed back the query result information to the industrial user.

[0063] The geographic location information of the publisher may be the geographic location where the lessee publishes the industrial order. The query result information may be obtained by filtering the target industrial orders based on the geographic location information of the publisher and the target region information, and corresponding industrial orders may be obtained, corresponding to the query result information.

[0064] Continuing with the previous example, after filtering out 30 target industrial orders that match the query keyword "industrial equipment for toy manufacturing," further filtering can be performed based on the target region information being Tianjin and the publisher's geographic location information. Specifically, based on the publisher's geographic location information, it can be determined that the publisher's geographic location information for 8 industrial orders is Tianjin, the publisher's geographic location information for 10 industrial orders is Beijing, the publisher's geographic location information for 5 industrial orders is City A in Hebei Province, and the publisher's geographic location information for 7 industrial orders is City A in Shandong Province. Therefore, filtering can be performed based on the target region information being Tianjin and the publisher's geographic location information being Tianjin, thereby obtaining 8 industrial orders, thereby obtaining query result information, and feeding the query result information back to the industrial user.

[0065] The technical solution provided by the embodiment of the present invention obtains query keywords and target dialect types that match the query voice in response to the query voice input by the industrial user; obtains target industrial orders that match the query keywords from various industrial orders; determines target region information that matches the industrial user based on the target dialect type; and filters query result information from each target industrial order based on the geographic location information of the publisher and the target region information included in each target industrial order, and feeds back the query result information to the industrial user. The technical solution of the embodiment of the present invention not only analyzes the language content in the query voice of the industrial user, but also further analyzes the dialect type of the query voice, and then can quickly filter out the information actually needed by the industrial user through the platform in combination with the dialect type. While solving the problem of practitioners having difficulty using text input methods through language input, it further saves search time and improves search efficiency.

[0066] Figure 2 This is a flowchart of another information query method provided by an embodiment of the present invention. This embodiment is optimized based on the above embodiments. In this embodiment, after obtaining the query keywords and target dialect type that match the query voice input by the industrial user in response to the query voice, it also includes: a target query object recognition module.

[0067] Accordingly, the method specifically includes the following steps:

[0068] S210 : In response to a query voice input by an industrial user, obtain query keywords and a target dialect type that match the query voice.

[0069] S220: Identify a target query object from the obtained query keywords.

[0070] The target query object may be a query object identified in the query keyword.

[0071] For example, assuming that the dialect type used by an industrial user is Tianjin dialect, when the user makes a voice query, for example, the user says "query for industrial equipment for manufacturing toys", the intelligent voice assistant can obtain the user's query keywords as "manufacturing", "toys" and "industrial equipment", and further identify that the target query object is "industrial equipment", and can identify that the user's dialect type is Tianjin dialect.

[0072] S230: Match the target query object in a standardized naming library, and when it is determined that the target query object is not located in the standardized naming library, match the target query object with an alias library.

[0073] Generally speaking, an industrial order is usually an order for a specific object, which can be a specific large manufacturing equipment or a specific industrial manufacturing product, etc. Among them, the standardized naming library generally stores the standardized names of various objects that may appear in industrial orders, and the alias library generally stores the aliases of one or more of the above objects.

[0074] In this embodiment, the inventor further considered industrial users in different regions who may call the same object by different aliases. That is, the alias of the object also carries the possible regional information of the industrial user. Furthermore, the regional information corresponding to the industrial user can be further determined based on the alias.

[0075] S240. Obtain the target alias that matches the target query object.

[0076] Exemplarily, assume that the dialect type used by the industrial user is the Tianjin dialect. When the user conducts a voice query, for example, the user says "Query which enterprise leases an excavator", then the intelligent voice assistant can obtain the query keywords of the user as "lease" and "excavator". Further, it can identify that the target query object is "excavator", and can also identify that the dialect type of the user is the Hakka dialect. Assume that the target query object "excavator" is matched in the standardized naming library, and when it is determined that the target query object "excavator" is not in the standardized naming library, correspondingly, the target query object "excavator" is matched with the alias library to obtain the target alias that matches the target query object "excavator".

[0077] S250. Query the second mapping relationship between the alias and the regional tendency, and obtain the target regional tendency that matches the target alias.

[0078] Among them, the regional tendency can be that different aliases correspond to different regional characteristics and have different regional tendencies. The second mapping relationship can be that different aliases correspond to different regional tendencies, so as to form a corresponding mapping relationship.

[0079] Continuing with the previous example, when the target alias that matches the target query object "excavator" is obtained, the corresponding target regional tendency can be obtained as "southern Fujian", that is, the five regions of Xiamen, Quanzhou, Zhangzhou, Putian, and Longyan.

[0080] S260. Use the standardized naming corresponding to the target alias to replace the target query object in the query keyword.

[0081] For example, assuming that the dialect type used by the industrial user is Tianjin dialect, when the user performs a voice query, the query keywords are "lease" and "industrial equipment A", the target query object "industrial equipment A" is identified, and the target query object "industrial equipment A" is matched in the standardized naming library. When it is determined that the target query object "industrial equipment A" is not in the standardized naming library, the target query object "industrial equipment A" is matched with the alias library, and the target alias matched by the target query object is determined to be "industrial equipment AA", and the standardized name "industrial equipment BB" corresponding to the target alias "industrial equipment AA" is obtained, and "industrial equipment BB" is used to replace the target query object "industrial equipment A" in the query keyword.

[0082] S270: Obtain target industrial orders matching the query keyword from various industrial orders.

[0083] S280: Determine target region information matching the industrial user based on the target dialect type and the target region preference.

[0084] S290. Filter and obtain query result information from each target industrial order based on the geographic location information of the publisher and the target region information included in each target industrial order, and feed back the query result information to the industrial user.

[0085] The technical solution provided by the embodiment of the present invention obtains query keywords and target dialect types that match the query voice in response to the query voice input by the industrial user; identifies the target query object in the obtained query keywords; matches the target query object in a standardized naming library, and when it is determined that the target query object is not located in the standardized naming library, matches the target query object with an alias library; obtains a target alias that matches the target query object, queries a second mapping relationship between the alias and the regional tendency, and obtains a target regional tendency that matches the target alias; and replaces the target query object in the query keyword with the standardized name corresponding to the target alias; obtains a target industrial order that matches the query keyword from each industrial order; determines the target regional information that matches the industrial user based on the target dialect type and the target regional tendency; and filters query result information from each target industrial order based on the geographic location information of the publisher and the target regional information included in each target industrial order, and feeds the query result information back to the industrial user. The technical solution of the embodiment of the present invention further considers the regional tendency of the alias included in the industrial user's voice when determining the regional information of the industrial user, thereby making the determination of the regional information more accurate, and then the user's query voice can be searched more accurately, further saving search time and improving search efficiency.

[0086] Figure 3 This is a flowchart of another information query method provided by an embodiment of the present invention. This embodiment is optimized based on the above embodiments. In this embodiment, when determining the regional information of industrial users, in addition to considering the query keywords matching the query speech and the target dialect type, the dialect standardization index of the query speech is further considered.

[0087] Accordingly, the method specifically includes the following steps:

[0088] S310 . In response to a query voice input by an industrial user, obtain query keywords, a target dialect type, and a dialect standardization index that match the query voice.

[0089] The dialect standardization index may refer to the degree of dialect standardization of the query speech.

[0090] In the embodiment, the inventors further consider that although users in a certain area all use the same type of dialect, the users are located in different geographical locations within the area and the degree of standardization of their dialects is also different.

[0091] In a specific example, the degree of standardization of Northeastern dialect among users in central Heilongjiang Province is much higher than that among users in the border areas of Heilongjiang Province.

[0092] Optionally, in response to a query voice input by an industrial user, obtaining a target dialect type and a dialect standardization index that matches the query voice may include:

[0093] The query speech is input into a pre-trained dialect recognition model, and the probability values ​​output by the dialect recognition model for the query speech to belong to various dialect types are obtained; the dialect type corresponding to the highest probability value is determined as the target dialect type, and based on the probability value corresponding to the target dialect type, the dialect standardization index matching the query speech is calculated.

[0094] The dialect recognition model can be trained using query speech input from multiple industrial users. Accordingly, after a query speech is input into the dialect recognition model, the model performs multi-classification recognition on the query speech to obtain the probability values ​​of the query speech belonging to different dialect types.

[0095] For example, assuming that the dialect type used by an industrial user is Tianjin dialect, when the user makes a voice query, the query voice is input into a pre-trained dialect recognition model, and the probability value output by the dialect recognition model is obtained, indicating that the query voice belongs to each dialect type.

[0096] Specifically, assume that the query speech has a probability of 90% that it belongs to the Tianjin dialect, a probability of 50% that it belongs to the Beijing dialect, and a probability of 70% that it belongs to the Mandarin dialect. Since the probability of the Tianjin dialect is 90%, which is the highest probability value, the dialect type corresponding to the highest probability value is determined as the target dialect type of the query speech, namely the Tianjin dialect. Furthermore, based on the probability value corresponding to the target dialect type, the dialect standardization index matching the query speech is calculated, which is also 90%.

[0097] The benefit of this setup is that by feeding the query into a pre-trained dialect recognition model, the probability of the query belonging to each dialect type is determined. The dialect type with the highest probability is then identified as the target dialect type, and the dialect standardization index that matches the query is calculated. This allows for more accurate identification of the region of industrial users based on the dialect standardization index, further improving search efficiency.

[0098] S320: Obtain target industrial orders matching the query keyword from various industrial orders.

[0099] S330: Acquire platform login information corresponding to the industrial user, and acquire target enterprise registration location information and target permanent location information matching the industrial user based on the platform login information.

[0100] S340: Input the target enterprise registration location information, target permanent location information, target dialect type, and dialect standardization index of the industrial user into a pre-trained region recognition model to obtain target region information matching the industrial user.

[0101] For example, assuming that the dialect type used by the industrial user is Tianjin dialect, when the industrial user performs a voice query, for example, the industrial user says "query for industrial equipment for manufacturing toys", the corresponding query keywords can be found, and it can be identified that the dialect type of the industrial user is Tianjin dialect.

[0102] At the same time, the platform login information corresponding to the industrial user must be obtained. Based on the platform login information, the target enterprise registration location information, target permanent residence information, and dialect standardization index matching the industrial user are obtained. Specifically, the target enterprise registration location information matching the industrial user may be Beijing, the target permanent residence information may be Tianjin, and the dialect standardization index may be 90%.

[0103] Furthermore, the industrial user's target enterprise registration location information (Beijing), target permanent residence information (Tianjin), target dialect type (Tianjin dialect), and dialect standardization index (90%) are input into the pre-trained region recognition model to obtain the target region information matching the industrial user, namely Tianjin. Specifically, although the enterprise's registration location information is Beijing, the target permanent residence information is Tianjin, the target dialect type is Tianjin dialect, and the dialect standardization index is 90%. After training with multiple training samples, the region recognition model determines that the industrial user is likely located in Tianjin, and thus determines that the target region information matching the industrial user is Tianjin.

[0104] S350: Filter and obtain query result information from each target industrial order based on the geographic location information of the publisher and the target region information included in each target industrial order, and feed back the query result information to the industrial user.

[0105] The technical solution provided by the embodiment of the present invention obtains query keywords, target dialect type, and dialect standardization index that match the query voice input by an industrial user in response to the query voice; obtains target industrial orders that match the query keywords from various industrial orders; obtains platform login information corresponding to the industrial user, and obtains target enterprise registration location information and target permanent location information that match the industrial user based on the platform login information; inputs the target enterprise registration location information, target permanent location information, target dialect type, and dialect standardization index of the industrial user into a pre-trained region recognition model to obtain target region information that matches the industrial user; and filters query result information from each target industrial order based on the geographic location information of the publisher and the target region information included in each target industrial order, and feeds the query result information back to the industrial user. The target region information that matches the industrial user can be more accurately determined based on the query keywords, target dialect type, and dialect standardization index that match the query voice, thereby enabling more accurate searches, saving search time, and improving search efficiency and search accuracy.

[0106] Figure 4 This is a schematic diagram of the structure of an information query device provided by an embodiment of the present invention. The information query device provided by this embodiment can be implemented by software and / or hardware and can be configured in a server or terminal device. Figure 4 As shown, the device may specifically include: a query keyword and target dialect type acquisition module 410, a target industrial order acquisition module 420, a target region information determination module 430 and a query result information feedback module 440.

[0107] The query keyword and target dialect type acquisition module 410 is configured to respond to a query voice input by an industrial user and acquire a query keyword and a target dialect type that match the query voice.

[0108] The target industrial order acquisition module 420 is used to acquire the target industrial order matching the query keyword from various industrial orders;

[0109] A target region information determination module 430 is configured to determine target region information matching the industrial user based on the target dialect type;

[0110] The query result information feedback module 440 is used to filter the query result information from each target industrial order according to the geographic location information of the publisher and the target region information included in each target industrial order, and feed back the query result information to the industrial user.

[0111] The technical solution provided by the embodiment of the present invention obtains query keywords and target dialect types that match the query voice in response to the query voice input by the industrial user; obtains target industrial orders that match the query keywords from various industrial orders; determines target region information that matches the industrial user based on the target dialect type; and filters query result information from each target industrial order based on the geographic location information of the publisher and the target region information included in each target industrial order, and feeds back the query result information to the industrial user. The technical solution of the embodiment of the present invention not only analyzes the language content in the query voice of the industrial user, but also further analyzes the dialect type of the query voice, and then can quickly filter out the information actually needed by the industrial user through the platform in combination with the dialect type. While solving the problem of practitioners having difficulty using text input methods through language input, it further saves search time and improves search efficiency.

[0112] Based on the above embodiments, the target region information determination module 430 may be specifically configured to query a first mapping relationship between a dialect type and region information, and obtain target region information matching the target dialect type based on the first mapping relationship.

[0113] Based on the above embodiments, the target region information determination module 430 can be specifically used to: obtain the platform login information corresponding to the industrial user, and obtain the target enterprise registration location information and target permanent residence information matching the industrial user based on the platform login information; input the target enterprise registration location information, target permanent residence information and target dialect type of the industrial user into a pre-trained region recognition model to obtain the target region information matching the industrial user.

[0114] Based on the above embodiments, it also includes a target query object identification module, which can be used to: after obtaining the query keyword and target dialect type matching the query voice in response to the query voice input by the industrial user, identify the target query object in the obtained query keyword; match the target query object in a standardized naming library, and when it is determined that the target query object is not located in the standardized naming library, match the target query object with an alias library; obtain a target alias matching the target query object, and use the standardized name corresponding to the target alias to replace the target query object in the query keyword.

[0115] On the basis of the above embodiments, it also includes a target regional tendency acquisition module, which can be used to: after obtaining the target alias that matches the target query object, it also includes: querying the second mapping relationship between the alias and the regional tendency to obtain the target regional tendency that matches the target alias.

[0116] Based on the above embodiments, the target region information determination module 430 may be specifically configured to determine target region information matching the industrial user according to the target dialect type and the target region tendency.

[0117] Based on the above embodiments, the query keyword and target dialect type acquisition module 410 may include: a query voice response unit, which is used to respond to the query voice input by the industrial user and obtain the query keyword, target dialect type and dialect standardization index that match the query voice.

[0118] Based on the above embodiments, the target region information determination module 430 can be specifically used to: obtain the platform login information corresponding to the industrial user, and obtain the target enterprise registration location information and target permanent residence information matching the industrial user based on the platform login information; input the target enterprise registration location information, target permanent residence information, target dialect type and dialect standardization index of the industrial user into a pre-trained region recognition model to obtain the target region information matching the industrial user.

[0119] Based on the above embodiments, the query voice response unit can be specifically used to: input the query voice into a pre-trained dialect recognition model, obtain the probability value of the query voice belonging to each dialect type output by the dialect recognition model; determine the dialect type corresponding to the highest probability value as the target dialect type, and calculate the dialect standardization index matching the query voice based on the probability value corresponding to the target dialect type.

[0120] The above-mentioned information query device can execute the information query method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0121] Figure 5 FIG. 1 is a schematic diagram of the structure of a computer device provided by another embodiment of the present invention. Figure 5 As shown, the device includes a processor 510, a memory 520, an input device 530, and an output device 540; the number of processors 510 in the device can be one or more. Figure 5 In the embodiment, a processor 510 is used as an example; the processor 510, the memory 520, the input device 530 and the output device 540 in the device can be connected via a bus or other means. Figure 5 The bus connection is taken as an example.

[0122] The memory 520, as a computer-readable storage medium, can be used to store software programs, computer executable programs, and modules, such as program instructions / modules corresponding to the information query method in the embodiment of the present invention (e.g., the query keyword and target dialect type acquisition module 410, the target industrial order acquisition module 420, the target region information determination module 430, and the query result information feedback module 440). The processor 510 executes the various functional applications and data processing of the device by running the software programs, instructions, and modules stored in the memory 520, that is, implements the above-mentioned information query method. The method includes: in response to a query voice input by an industrial user, obtaining a query keyword and a target dialect type that match the query voice; obtaining a target industrial order that matches the query keyword from each industrial order; determining the target region information that matches the industrial user based on the target dialect type; filtering the query result information from each target industrial order based on the publisher's geographic location information and the target region information included in each target industrial order, and feeding the query result information back to the industrial user.

[0123] The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created based on the use of the terminal, etc. In addition, the memory 520 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 520 may further include a memory remotely located relative to the processor 510, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0124] The input device 530 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 540 may include a display device such as a display screen.

[0125] An embodiment of the present invention also provides a computer-readable storage medium, wherein the computer-executable instructions are used to execute an information query method when executed by a computer processor, the method comprising: in response to a query voice input by an industrial user, obtaining query keywords and a target dialect type that match the query voice; obtaining target industrial orders that match the query keywords from various industrial orders; determining target region information that matches the industrial user based on the target dialect type; and filtering query result information from each target industrial order based on the publisher's geographic location information and the target region information included in each target industrial order, and feeding back the query result information to the industrial user.

[0126] Of course, the computer-readable storage medium provided in the embodiment of the present invention has computer-executable instructions that are not limited to the method operations described above, and can also execute related operations in the information query method provided in any embodiment of the present invention.

[0127] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0128] It is worth noting that in the embodiment of the above-mentioned information query device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0129] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the concept of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. An information query method, characterized in that: Executed by electronic trading platforms in the industrial manufacturing sector, including: In response to a query voice input by an industrial user, obtaining a query keyword and a target dialect type that match the query voice; Obtaining target industrial orders matching the query keyword from various industrial orders; Determining target region information matching the industrial user according to the target dialect type; Filtering query result information from each target industrial order based on the geographic location information of the issuer and the target region information included in each target industrial order, and feeding back the query result information to the industrial user; The step of determining target region information matching the industrial user based on the target dialect type includes: querying a first mapping relationship between a dialect type and region information, and acquiring target region information matching the target dialect type based on the first mapping relationship; The first mapping relationship is a mapping relationship between a dialect type and one or more pieces of regional information; After obtaining the query keyword and the target dialect type matching the query voice in response to the query voice input by the industrial user, the method further includes: Identifying a target query object among the acquired query keywords; Matching the target query object in a standardized naming library, and when it is determined that the target query object is not in the standardized naming library, matching the target query object with an alias library; Obtaining a target alias that matches the target query object, and replacing the target query object in the query keyword with a standardized name corresponding to the target alias; Wherein, after obtaining the target alias matching the target query object, the method further includes: Querying a second mapping relationship between the alias and the regional orientation to obtain a target regional orientation matching the target alias; The determining, based on the target dialect type, target region information matching the industrial user includes: Target region information matching the industrial user is determined based on the target dialect type and the target region tendency.

2. The method according to claim 1, characterized in that The determining, based on the target dialect type, target region information matching the industrial user includes: Obtaining platform login information corresponding to the industrial user, and obtaining target enterprise registration location information and target permanent location information matching the industrial user based on the platform login information; The target enterprise registration location information, target permanent location information and target dialect type of the industrial user are input into a pre-trained region recognition model to obtain target region information matching the industrial user.

3. The method according to claim 1, characterized in that The step of obtaining, in response to a query voice input by an industrial user, a query keyword and a target dialect type that match the query voice comprises: In response to a query voice input by an industrial user, obtaining a query keyword, a target dialect type, and a dialect standardization index that matches the query voice; The determining, based on the target dialect type, target region information matching the industrial user includes: Obtaining platform login information corresponding to the industrial user, and obtaining target enterprise registration location information and target permanent location information matching the industrial user based on the platform login information; The target enterprise registration location information, target permanent location information, target dialect type and dialect standardization index of the industrial user are input into a pre-trained region recognition model to obtain target region information matching the industrial user.

4. The method according to claim 3, characterized in that The step of obtaining, in response to a query voice input by an industrial user, a target dialect type and a dialect standardization index that matches the query voice comprises: Inputting the query speech into a pre-trained dialect recognition model, and obtaining a probability value output by the dialect recognition model indicating that the query speech belongs to each dialect type; The dialect type corresponding to the highest probability value is determined as the target dialect type, and a dialect standardization index matching the query speech is calculated based on the probability value corresponding to the target dialect type.

5. An information query device, characterized in that: include: A query keyword and target dialect type acquisition module, configured to respond to a query voice input by an industrial user and acquire a query keyword and a target dialect type that match the query voice; A target industrial order acquisition module is used to acquire target industrial orders that match the query keyword from various industrial orders; A target region information determination module, configured to determine target region information matching the industrial user according to the target dialect type; a query result information feedback module, configured to filter query result information from each target industrial order based on the geographic location information of the issuer and the target region information included in each target industrial order, and feed back the query result information to the industrial user; The target region information determination module is configured to query a first mapping relationship between a dialect type and region information, and acquire target region information matching the target dialect type based on the first mapping relationship; The first mapping relationship is a mapping relationship between a dialect type and one or more pieces of regional information; The method further includes a target query object identification module, which is configured to: after obtaining a query keyword and a target dialect type matching the query voice in response to the query voice input by the industrial user, identify a target query object in the obtained query keyword; match the target query object in a standardized naming library, and when it is determined that the target query object is not in the standardized naming library, match the target query object with an alias library; obtain a target alias matching the target query object, and replace the target query object in the query keyword with a standardized name corresponding to the target alias; The method further includes a target region tendency acquisition module, which is configured to, after obtaining the target alias matching the target query object, further include: querying a second mapping relationship between the alias and the region tendency to obtain the target region tendency matching the target alias; The target region information determination module is configured to determine target region information that matches the industrial user based on the target dialect type and the target region tendency.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the information query method according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the information query method according to any one of claims 1 to 4 is implemented.

Images